Tootfinder

Yield Sec: illegal gambling operators captured 71% of Europe's online betting and casino market in 2024, or €80.65B, as regulators struggle with crypto casinos (Navya Menon/Bloomberg)
https://www.bloomberg.com/news/articles/20

New research has found that leading LLMs falter dramatically when exam questions are subtly reworded, raising doubts about whether these systems are truly capable of clinical reasoning.
https://www.computing.co.uk/news/2025/ai/t

Top AI models struggle with medical questions in real-world scenarios, study finds
AI systems that boast near-perfect scores on medical licensing exams may not be as clever as they seem.

Semantic-Aware Ship Detection with Vision-Language Integration
Jiahao Li, Jiancheng Pan, Yuze Sun, Xiaomeng Huang
https://arxiv.org/abs/2508.15930 https://…

Semantic-Aware Ship Detection with Vision-Language Integration
Ship detection in remote sensing imagery is a critical task with wide-ranging applications, such as maritime activity monitoring, shipping logistics, and environmental studies. However, existing methods often struggle to capture fine-grained semantic information, limiting their effectiveness in complex scenarios. To address these challenges, we propose a novel detection framework that combines Vision-Language Models (VLMs) with a multi-scale adaptive sliding window strategy. To facilitate Seman…

Democrats struggle to come up with a unified response to Trump's Iran strikes (NBC News)
https://www.nbcnews.com/politics/congress/democrats-struggle-unified-response-trump-iran-strikes-rcna214504
http://www.memeorandum.com/250624/p3#a250624p3

As a marketer by profession I feel this very deeply and struggle to find a way to communicate to fellow people on the left that the methods and tools for communicating messages and persuading masses of people SHOULD be used, as effectively as possible, to promote facts and values we align with.
I get that power is uncomfortable when so many parties visibly abuse it for malicious purposes.
But power in and of itself is a tools that needs to be wielded, and we should be cognizant about targeting it at changes that will improve our societies and help us and the planet.
Yes, don’t use power blindly. Don’t manipulate people. But using persuasive, effective tactics for mass communication to educate people on the truth and get them aboard initiatives that will help them??? Why is that evil?
It feels like the left sees power, influence, and thus marketing / PR / propaganda as too black-and-white. We need to be comfortable in navigating the grey. https://sauropods.win/@futurebird/114913847088444610

OwkinZero: Accelerating Biological Discovery with AI
Nathan Bigaud, Vincent Cabeli, Meltem Gurel, Arthur Pignet, John Klein, Gilles Wainrib, Eric Durand
https://arxiv.org/abs/2508.16315

OwkinZero: Accelerating Biological Discovery with AI
While large language models (LLMs) are rapidly advancing scientific research, they continue to struggle with core biological reasoning tasks essential for translational and biomedical discovery. To address this limitation, we created and curated eight comprehensive benchmark datasets comprising over 300,000 verifiable question-and-answer pairs, each targeting critical challenges in drug discovery including target druggability, modality suitability, and drug perturbation effects. Using this reso…

Liberals often struggle against populist narratives because the polar opposite of populism is elitism,
-- which carries much less appeal.
Here are some of the narratives that work to create the software of autocracy
https://www.politico.com/news/magazine/202

Hey everyone, every Tuesday, my friend @… asks for your help to feed her family. She can’t do it today (they’re trying to stay alive during a genocide) so she asked if I could do it on her behalf.

They need $500 each week for their family of 6.

Every single dollar makes a real difference 
If you’re unable to donate, please consider sharing – it might r…

Help Sehwel family with their medical treatment
I'm Joe in the UK, I've been in touch with Aseel from the Sehwel family for over a year now and have been following their difficult struggle to afford medication, shelter and food in Gaza. I'm creating this Chuffed campaign for the family to help afford these things and hopefully help them get out of Gaza when the opportunity arises. Here's Aseel's writing:

Accelerating a Linear Programming Algorithm on AMD GPUs
Xiyan Hu, Titus Parker, Connor Phillips, Yifa Yu
https://arxiv.org/abs/2508.16806 https://arxiv.org…

Accelerating a Linear Programming Algorithm on AMD GPUs
Linear Programming (LP) is a foundational optimization technique with widespread applications in finance, energy trading, and supply chain logistics. However, traditional Central Processing Unit (CPU)-based LP solvers often struggle to meet the latency and scalability demands of dynamic, high-dimensional industrial environments, creating a significant computational challenge. This project addresses these limitations by accelerating linear programming on AMD Graphics Processing Units (GPUs), lev…

Interesting that while Abundant SF's head is taking shots at Zohran, Abundance New York endorsed him.
(Fifth, but they still favored him over Cuomo. They said "Zohran Mamdani is more likely to prioritize the central crises facing New Yorkers.")

Multimodal Behavioral Patterns Analysis with Eye-Tracking and LLM-Based Reasoning
Dongyang Guo, Yasmeen Abdrabou, Enkeleda Thaqi, Enkelejda Kasneci
https://arxiv.org/abs/2507.18252

Multimodal Behavioral Patterns Analysis with Eye-Tracking and LLM-Based Reasoning
Eye-tracking data reveals valuable insights into users' cognitive states but is difficult to analyze due to its structured, non-linguistic nature. While large language models (LLMs) excel at reasoning over text, they struggle with temporal and numerical data. This paper presents a multimodal human-AI collaborative framework designed to enhance cognitive pattern extraction from eye-tracking signals. The framework includes: (1) a multi-stage pipeline using horizontal and vertical segmentation alo…

Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain
Kai Hu, Parfait Atchade-Adelomou, Carlo Adornetto, Adrian Mora-Carrero, Luis Alonso-Pastor, Ariel Noyman, Yubo Liu, Kent Larson
https://arxiv.org/abs/2508.16172

Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain
Understanding human behavior in urban environments is a crucial field within city sciences. However, collecting accurate behavioral data, particularly in newly developed areas, poses significant challenges. Recent advances in generative agents, powered by Large Language Models (LLMs), have shown promise in simulating human behaviors without relying on extensive datasets. Nevertheless, these methods often struggle with generating consistent, context-sensitive, and realistic behavioral outputs. T…

Memento: Note-Taking for Your Future Self
Chao Wan, Albert Gong, Mihir Mishra, Carl-Leander Henneking, Claas Beger, Kilian Q. Weinberger
https://arxiv.org/abs/2506.20642

Memento: Note-Taking for Your Future Self
Large language models (LLMs) excel at reasoning-only tasks, but struggle when reasoning must be tightly coupled with retrieval, as in multi-hop question answering. To overcome these limitations, we introduce a prompting strategy that first decomposes a complex question into smaller steps, then dynamically constructs a database of facts using LLMs, and finally pieces these facts together to solve the question. We show how this three-stage strategy, which we call Memento, can boost the performanc…

Cloud Native System for LLM Inference Serving
Minxian Xu, Junhan Liao, Jingfeng Wu, Yiyuan He, Kejiang Ye, Chengzhong Xu
https://arxiv.org/abs/2507.18007 https://

Cloud Native System for LLM Inference Serving
Large Language Models (LLMs) are revolutionizing numerous industries, but their substantial computational demands create challenges for efficient deployment, particularly in cloud environments. Traditional approaches to inference serving often struggle with resource inefficiencies, leading to high operational costs, latency issues, and limited scalability. This article explores how Cloud Native technologies, such as containerization, microservices, and dynamic scheduling, can fundamentally impr…

Super-resolving frequency measurement with mode-selective quantum memory
Shicheng Zhang, Aonan Zhang, Ilse Maillette de Buy Wenniger, Paul M. Burdekin, Steven Sagona-Stophel, Anindya Rastogi, Sarah E. Thomas, Ian A. Walmsley
https://arxiv.org/abs/2506.20514

Super-resolving frequency measurement with mode-selective quantum memory
High-precision optical frequency measurement is indispensable to modern science and technology, yet conventional spectroscopic techniques struggle to resolve spectral features narrower than their bandwidth. Here, we introduce a unique platform for super-resolving frequency estimation utilizing a mode-selective atomic Raman quantum memory implemented in warm cesium vapor. By precisely engineering the light-matter interaction, our memory coherently stores the optimal temporal mode with high fidel…

Tasmanian leaders struggle with a basic fact: environment laws should protect the environment https://www.theguardian.com/commentisfree/2025/jun/23/tasmanian-leaders-environment-laws-protect

Generative AI for Vulnerability Detection in 6G Wireless Networks: Advances, Case Study, and Future Directions
Shuo Yang, Xinran Zheng, Jinfeng Xu, Jinze Li, Danyang Song, Zheyu Chen, Edith C. H. Ngai
https://arxiv.org/abs/2506.20488

Generative AI for Vulnerability Detection in 6G Wireless Networks: Advances, Case Study, and Future Directions
The rapid advancement of 6G wireless networks, IoT, and edge computing has significantly expanded the cyberattack surface, necessitating more intelligent and adaptive vulnerability detection mechanisms. Traditional security methods, while foundational, struggle with zero-day exploits, adversarial threats, and context-dependent vulnerabilities in highly dynamic network environments. Generative AI (GAI) emerges as a transformative solution, leveraging synthetic data generation, multimodal reasoni…

ICWLM: A Multi-Task Wireless Large Model via In-Context Learning
Yuxuan Wen, Xiaoming Chen, Maojun Zhang, Zhaoyang Zhang
https://arxiv.org/abs/2507.18167 https://

ICWLM: A Multi-Task Wireless Large Model via In-Context Learning
The rapid evolution of wireless communication technologies, particularly massive multiple-input multiple-output (mMIMO) and millimeter-wave (mmWave), introduces significant network complexity and computational demands. Significant research efforts have been made to improve physical layer performance by resorting to deep learning (DL) methods, which, however, are usually task-specific and struggle with data scarcity and generalization. To address these challenges, we propose a novel In-Context W…

IndieFake Dataset: A Benchmark Dataset for Audio Deepfake Detection
Abhay Kumar, Kunal Verma, Omkar More
https://arxiv.org/abs/2506.19014 https://

IndieFake Dataset: A Benchmark Dataset for Audio Deepfake Detection
Advancements in audio deepfake technology offers benefits like AI assistants, better accessibility for speech impairments, and enhanced entertainment. However, it also poses significant risks to security, privacy, and trust in digital communications. Detecting and mitigating these threats requires comprehensive datasets. Existing datasets lack diverse ethnic accents, making them inadequate for many real-world scenarios. Consequently, models trained on these datasets struggle to detect audio dee…

@… I hope you have figured it out for today.
Alas, tomorrow, the struggle begins again.

How Instructional Sequence and Personalized Support Impact Diagnostic Strategy Learning
Fatma Bet\"ul G\"ure\c{s}, Tanya Nazaretsky, Bahar Radmehr, Martina Rau, Tanja K\"aser
https://arxiv.org/abs/2507.17760

How Instructional Sequence and Personalized Support Impact Diagnostic Strategy Learning
Supporting students in developing effective diagnostic reasoning is a key challenge in various educational domains. Novices often struggle with cognitive biases such as premature closure and over-reliance on heuristics. Scenario-based learning (SBL) can address these challenges by offering realistic case experiences and iterative practice, but the optimal sequencing of instruction and problem-solving activities remains unclear. This study examines how personalized support can be incorporated in…

HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation
Xinyu Wang, Jinghua Hou, Zhe Liu, Yingying Zhu
https://arxiv.org/abs/2507.18575 https://

HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation
Transformer-based methods have demonstrated remarkable capabilities in 3D semantic segmentation through their powerful attention mechanisms, but the quadratic complexity limits their modeling of long-range dependencies in large-scale point clouds. While recent Mamba-based approaches offer efficient processing with linear complexity, they struggle with feature representation when extracting 3D features. However, effectively combining these complementary strengths remains an open challenge in thi…

NEAR$^2$: A Nested Embedding Approach to Efficient Product Retrieval and Ranking
Shenbin Qian, Diptesh Kanojia, Samarth Agrawal, Hadeel Saadany, Swapnil Bhosale, Constantin Orasan, Zhe Wu
https://arxiv.org/abs/2506.19743

NEAR$^2$: A Nested Embedding Approach to Efficient Product Retrieval and Ranking
E-commerce information retrieval (IR) systems struggle to simultaneously achieve high accuracy in interpreting complex user queries and maintain efficient processing of vast product catalogs. The dual challenge lies in precisely matching user intent with relevant products while managing the computational demands of real-time search across massive inventories. In this paper, we propose a Nested Embedding Approach to product Retrieval and Ranking, called NEAR$^2$, which can achieve up to $12$ tim…

Accurate identification of communication between multiple interacting neural populations
Belle Liu, Jacob Sacks, Matthew D. Golub
https://arxiv.org/abs/2506.19094

Accurate identification of communication between multiple interacting neural populations
Neural recording technologies now enable simultaneous recording of population activity across many brain regions, motivating the development of data-driven models of communication between brain regions. However, existing models can struggle to disentangle the sources that influence recorded neural populations, leading to inaccurate portraits of inter-regional communication. Here, we introduce Multi-Region Latent Factor Analysis via Dynamical Systems (MR-LFADS), a sequential variational autoenco…

LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow
Kaiyan Chang, Wenlong Zhu, Shengwen Liang, Huawei Li, Ying Wang
https://arxiv.org/abs/2508.17826

LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow
Accurate and fast performance prediction for dataflow-based accelerators is vital for efficient hardware design and design space exploration, yet existing methods struggle to generalize across architectures, applications, and input-dependent control flows. We present LLMulator, a progressive numeric modeling framework leveraging the program semantic knowledge of pre-trained large language models (LLMs) for robust, hardware- and application-aware prediction. Our numeric model treats performance …

GeoAvatar: Adaptive Geometrical Gaussian Splatting for 3D Head Avatar
SeungJun Moon, Hah Min Lew, Seungeun Lee, Ji-Su Kang, Gyeong-Moon Park
https://arxiv.org/abs/2507.18155 htt…

GeoAvatar: Adaptive Geometrical Gaussian Splatting for 3D Head Avatar
Despite recent progress in 3D head avatar generation, balancing identity preservation, i.e., reconstruction, with novel poses and expressions, i.e., animation, remains a challenge. Existing methods struggle to adapt Gaussians to varying geometrical deviations across facial regions, resulting in suboptimal quality. To address this, we propose GeoAvatar, a framework for adaptive geometrical Gaussian Splatting. GeoAvatar leverages Adaptive Pre-allocation Stage (APS), an unsupervised method that se…

“there’s amazing grassroots organizing led by poor and dispossessed people that’s happening right now…
there’s kind of an awakening happening,
but I think instead of looking to our political leaders or looking to some of the more established folks out there.”
https://

There’s resistance happening all around us, we’re just not seeing it
“I think we are seeing, in this moment, this emergent struggle—this survival struggle that's happening across the country,” Rev. Dr. Liz Theoharis and Noam Sandweiss-Back tell us. “And again, the question is: How do we bring greater organization and coordination to it?”

Guiding Diffusion Models with Reinforcement Learning for Stable Molecule Generation
Zhijian Zhou, Junyi An, Zongkai Liu, Yunfei Shi, Xuan Zhang, Fenglei Cao, Chao Qu, Yuan Qi
https://arxiv.org/abs/2508.16521

Guiding Diffusion Models with Reinforcement Learning for Stable Molecule Generation
Generating physically realistic 3D molecular structures remains a core challenge in molecular generative modeling. While diffusion models equipped with equivariant neural networks have made progress in capturing molecular geometries, they often struggle to produce equilibrium structures that adhere to physical principles such as force field consistency. To bridge this gap, we propose Reinforcement Learning with Physical Feedback (RLPF), a novel framework that extends Denoising Diffusion Policy …

Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain
Kai Hu, Parfait Atchade-Adelomou, Carlo Adornetto, Adrian Mora-Carrero, Luis Alonso-Pastor, Ariel Noyman, Yubo Liu, Kent Larson
https://arxiv.org/abs/2508.16172

Graph RAG as Human Choice Model: Building a Data-Driven Mobility Agent with Preference Chain
Understanding human behavior in urban environments is a crucial field within city sciences. However, collecting accurate behavioral data, particularly in newly developed areas, poses significant challenges. Recent advances in generative agents, powered by Large Language Models (LLMs), have shown promise in simulating human behaviors without relying on extensive datasets. Nevertheless, these methods often struggle with generating consistent, context-sensitive, and realistic behavioral outputs. T…

SOT-MRAM Bitcell Scaling with BEOL Read Selectors: A DTCO Study
Yang Xiang, Fernando Garc\'ia-Redondo, Arvind Sharma, Van Dai Nguyen, Andrea Fantini, Philippe Matagne, Siddharth Rao, Subhali Subhechha, Lynn Verschueren, Mohammed Aftab Baig, Marie Garcia Bardon, Geert Hellings
https://arxiv.org/abs/2508.18250

SOT-MRAM Bitcell Scaling with BEOL Read Selectors: A DTCO Study
This work explores the cross-node scaling potential of SOT-MRAM for last-level caches (LLCs) under heterogeneous system scaling paradigm. We perform extensive Design-Technology Co-Optimization (DTCO) exercises to evaluate the bitcell footprint for different cell configurations at a representative 7 nm technology and to assess their implications on read and write power-performance. We crucially identify the MTJ routing struggle in conventional two-transistor one-resistor (2T1R) SOT-MRAMs as the …

X-Troll: eXplainable Detection of State-Sponsored Information Operations Agents
Lin Tian, Xiuzhen Zhang, Maria Myung-Hee Kim, Jennifer Biggs, Marian-Andrei Rizoiu
https://arxiv.org/abs/2508.16021

X-Troll: eXplainable Detection of State-Sponsored Information Operations Agents
State-sponsored trolls, malicious actors who deploy sophisticated linguistic manipulation in coordinated information campaigns, posing threats to online discourse integrity. While Large Language Models (LLMs) achieve strong performance on general natural language processing (NLP) tasks, they struggle with subtle propaganda detection and operate as ``black boxes'', providing no interpretable insights into manipulation strategies. This paper introduces X-Troll, a novel framework that bridges this…

Researchers: "chain of thought" techniques used by Anthropic, Google, OpenAI, and xAI show inconsistencies where chatbot answers contradict the stated reasoning (Cristina Criddle/Financial Times)
https://www.ft.com/content/b349f590-de84-455d-914a-cc5d9eef…

The struggle to get inside how AI models really work
Anthropic, Google  and OpenAI deploy ‘chains of thought’ to better understand the operations of AI systems

https://www.scworld.com/news/half-of-organizations-struggle-to-locate-backup-data-report-finds
Half of organizations struggle to locate backup data, report finds

Half of organizations struggle to locate backup data, report finds
Outdated cloud backup management strategies pose data loss and ransomware risks.

GraspMAS: Zero-Shot Language-driven Grasp Detection with Multi-Agent System
Quang Nguyen, Tri Le, Huy Nguyen, Thieu Vo, Tung D. Ta, Baoru Huang, Minh N. Vu, Anh Nguyen
https://arxiv.org/abs/2506.18448

GraspMAS: Zero-Shot Language-driven Grasp Detection with Multi-Agent System
Language-driven grasp detection has the potential to revolutionize human-robot interaction by allowing robots to understand and execute grasping tasks based on natural language commands. However, existing approaches face two key challenges. First, they often struggle to interpret complex text instructions or operate ineffectively in densely cluttered environments. Second, most methods require a training or finetuning step to adapt to new domains, limiting their generation in real-world applicat…

SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models
Dipayan Saha, Shams Tarek, Hasan Al Shaikh, Khan Thamid Hasan, Pavan Sai Nalluri, Md. Ajoad Hasan, Nashmin Alam, Jingbo Zhou, Sujan Kumar Saha, Mark Tehranipoor, Farimah Farahmandi
https://arxiv.org/abs/2506.20415…

SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models
Ensuring the security of complex system-on-chips (SoCs) designs is a critical imperative, yet traditional verification techniques struggle to keep pace due to significant challenges in automation, scalability, comprehensiveness, and adaptability. The advent of large language models (LLMs), with their remarkable capabilities in natural language understanding, code generation, and advanced reasoning, presents a new paradigm for tackling these issues. Moving beyond monolithic models, an agentic ap…

SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis
Wang Lingxiang, Quanzhi Fu, Wenjia Song, Gelei Deng, Yi Liu, Dan Williams, Ying Zhang
https://arxiv.org/abs/2506.17798

SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis
The integration of open-source third-party library dependencies in Java development introduces significant security risks when these libraries contain known vulnerabilities. Existing Software Composition Analysis (SCA) tools struggle to effectively detect vulnerable API usage from these libraries due to limitations in understanding API usage semantics and computational challenges in analyzing complex codebases, leading to inaccurate vulnerability alerts that burden development teams and delay c…

Learning-Based Distance Estimation for 360{\deg} Single-Sensor Setups
Yitong Quan, Benjamin Kiefer, Martin Messmer, Andreas Zell
https://arxiv.org/abs/2506.20586

Learning-Based Distance Estimation for 360° Single-Sensor Setups
Accurate distance estimation is a fundamental challenge in robotic perception, particularly in omnidirectional imaging, where traditional geometric methods struggle with lens distortions and environmental variability. In this work, we propose a neural network-based approach for monocular distance estimation using a single 360° fisheye lens camera. Unlike classical trigonometric techniques that rely on precise lens calibration, our method directly learns and infers the distance of objects from …

Stock is rising for Cowboys CB in 1st week of training camp https://insidethestar.com/stock-is-rising-for-cowboys-cb-in-1st-week-of-training-camp

UniMind: Unleashing the Power of LLMs for Unified Multi-Task Brain Decoding
Weiheng Lu, Chunfeng Song, Jiamin Wu, Pengyu Zhu, Yuchen Zhou, Weijian Mai, Qihao Zheng, Wanli Ouyang
https://arxiv.org/abs/2506.18962

UniMind: Unleashing the Power of LLMs for Unified Multi-Task Brain Decoding
Decoding human brain activity from electroencephalography (EEG) signals is a central challenge at the intersection of neuroscience and artificial intelligence, enabling diverse applications in mental state assessment, clinical monitoring, and human-machine interaction. Recent efforts have extensively explored EEG-based brain foundation models for generalized brain decoding, employing large-scale training on multiple datasets. However, most of these attempts struggle with generalizability and fa…

Mixed-Mode In-Memory Computing: Towards High-Performance Logic Processing In A Memristive Crossbar Array
Nan Du, Ilia Polian, Christopher Bengel, Kefeng Li, Ziang Chen, Xianyue Zhao, Uwe Huebner, Li-Wei Chen, Feng Liu, Massimiliano Di Ventra, Stephan Menzel, Heidemarie Krueger
https://arxiv.org/abs/2506.19063

Mixed-Mode In-Memory Computing: Towards High-Performance Logic Processing In A Memristive Crossbar Array
In-memory computing is a promising alternative to traditional computer designs, as it helps overcome performance limits caused by the separation of memory and processing units. However, many current approaches struggle with unreliable device behavior, which affects data accuracy and efficiency. In this work, the authors present a new computing method that combines two types of operations,those based on electrical resistance and those based on voltage, within each memory cell. This design improv…

RightTyper: Effective and Efficient Type Annotation for Python
Juan Altmayer Pizzorno, Emery D. Berger
https://arxiv.org/abs/2507.16051 https://

RightTyper: Effective and Efficient Type Annotation for Python
Python type annotations bring the benefits of static type checking to the language. However, manually writing annotations can be time-consuming and tedious. The result is that most real-world Python code remains largely untyped. Past approaches to annotating types in Python code fall short in a number of ways. Static approaches struggle with dynamic features and infer overly broad types. AI-based methods are inherently unsound and can miss rare or user-defined types. Dynamic methods can impose …

OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
Yu Liu, Yanbing Liu, Fangfang Yuan, Cong Cao, Youbang Sun, Kun Peng, WeiZhuo Chen, Jianjun Li, Zhiyuan Ma
https://arxiv.org/abs/2508.16438

OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
Recent advances in large language models (LLMs) and dense retrievers have driven significant progress in retrieval-augmented generation (RAG). However, existing approaches face significant challenges in complex reasoning-oriented multi-hop retrieval tasks: 1) Ineffective reasoning-oriented planning: Prior methods struggle to generate robust multi-step plans for complex queries, as rule-based decomposers perform poorly on out-of-template questions. 2) Suboptimal reasoning-driven retrieval: Relat…

DCMF: A Dynamic Context Monitoring and Caching Framework for Context Management Platforms
Ashish Manchanda, Prem Prakash Jayaraman, Abhik Banerjee, Kaneez Fizza, Arkady Zaslavsky
https://arxiv.org/abs/2506.17226

DCMF: A Dynamic Context Monitoring and Caching Framework for Context Management Platforms
The rise of context-aware IoT applications has increased the demand for timely and accurate context information. Context is derived by aggregating and inferring from dynamic IoT data, making it highly volatile and posing challenges in maintaining freshness and real-time accessibility. Caching is a potential solution, but traditional policies struggle with the transient nature of context in IoT (e.g., ensuring real-time access for frequent queries or handling fast-changing data). To address this…

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
Shuang Ao, Yi Dong, Jinwei Hu, Sarvapali Ramchurn
https://arxiv.org/abs/2506.18931

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs
Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing susceptibility to harmful outputs. Existing safety alignment methods struggle to capture complex parameter shifts, leading to suboptimal safety-utility trade-offs. To address this issue, we propose Safe Pruning LoRA (SPLoRA), a novel pruning-based approach that selectively remove…

G-SEED: A Spatio-temporal Encoding Framework for Forest and Grassland Data Based on GeoSOT
Xuan Ouyang, Xinwen Yu, Yan Chen, Guang Deng, Xuanxin Liu
https://arxiv.org/abs/2506.18094

G-SEED: A Spatio-temporal Encoding Framework for Forest and Grassland Data Based on GeoSOT
In recent years, the rapid development of remote sensing, Unmanned Aerial Vehicles, and IoT technologies has led to an explosive growth in spatio-temporal forest and grassland data, which are increasingly multimodal, heterogeneous, and subject to continuous updates. However, existing Geographic Information Systems (GIS)-based systems struggle to integrate and manage of such large-scale and diverse data sources. To address these challenges, this paper proposes G-SEED (GeoSOT-based Scalable Encod…

LLM-as-classifier: Semi-Supervised, Iterative Framework for Hierarchical Text Classification using Large Language Models
Doohee You, Andy Parisi, Zach Vander Velden, Lara Dantas Inojosa
https://arxiv.org/abs/2508.16478

LLM-as-classifier: Semi-Supervised, Iterative Framework for Hierarchical Text Classification using Large Language Models
The advent of Large Language Models (LLMs) has provided unprecedented capabilities for analyzing unstructured text data. However, deploying these models as reliable, robust, and scalable classifiers in production environments presents significant methodological challenges. Standard fine-tuning approaches can be resource-intensive and often struggle with the dynamic nature of real-world data distributions, which is common in the industry. In this paper, we propose a comprehensive, semi-supervise…

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction
Sara Rojas, Matthieu Armando, Bernard Ghamen, Philippe Weinzaepfel, Vincent Leroy, Gregory Rogez
https://arxiv.org/abs/2508.16433

HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction
Recovering the 3D geometry of a scene from a sparse set of uncalibrated images is a long-standing problem in computer vision. While recent learning-based approaches such as DUSt3R and MASt3R have demonstrated impressive results by directly predicting dense scene geometry, they are primarily trained on outdoor scenes with static environments and struggle to handle human-centric scenarios. In this work, we introduce HAMSt3R, an extension of MASt3R for joint human and scene 3D reconstruction from …

Sources: Adani Group has shelved plans for a consumer super app amid losses and internal turmoil, as Reliance and Tata also struggle to scale their platforms (Bloomberg)
https://www.bloomberg.com/news/articles/2025-07-2…

Multi-objective Portfolio Optimization Via Gradient Descent
Christian Oliva, Pedro R. Ventura, Luis F. Lago-Fern\'andez
https://arxiv.org/abs/2507.16717 https://

Multi-objective Portfolio Optimization Via Gradient Descent
Traditional approaches to portfolio optimization, often rooted in Modern Portfolio Theory and solved via quadratic programming or evolutionary algorithms, struggle with scalability or flexibility, especially in scenarios involving complex constraints, large datasets and/or multiple conflicting objectives. To address these challenges, we introduce a benchmark framework for multi-objective portfolio optimization (MPO) using gradient descent with automatic differentiation. Our method supports any …

DREAM Will Show It All: How Ukraine’s Reconstruction Is Going, How Much It Costs—and Who Pays: https://benborges.xyz/2025/08/20/dream-will-show-it-all.html

MyGO: Make your Goals Obvious, Avoiding Semantic Confusion in Prostate Cancer Lesion Region Segmentation
Zhengcheng Lin (City University of Macau), Zuobin Ying (City University of Macau), Zhenyu Li (Shandong University), Zhenyu Liu (Chinese Academy of Sciences), Jian Lu (Peking University), Weiping Ding (Nantong University)
https://

MyGO: Make your Goals Obvious, Avoiding Semantic Confusion in Prostate Cancer Lesion Region Segmentation
Early diagnosis and accurate identification of lesion location and progression in prostate cancer (PCa) are critical for assisting clinicians in formulating effective treatment strategies. However, due to the high semantic homogeneity between lesion and non-lesion areas, existing medical image segmentation methods often struggle to accurately comprehend lesion semantics, resulting in the problem of semantic confusion. To address this challenge, we propose a novel Pixel Anchor Module, which guid…

Zohran Mamdani’s apparent victory late Tuesday night represented a sharp rebuke of the Democratic Party establishment
It represented, he said, the ascendance of a new Democratic coalition, one that prioritized the needs of the working class over those of the elite.
“We have won because New Yorkers have stood up for a city they can afford,” he said.
“A city where they can do more than just struggle. One where those who toil in the night can enjoy the fruits of their labor in…

In Joyful Speech, Mamdani Vows to Work for ‘Each and Every New Yorker’
A crowd in Queens celebrated the triumph of Zohran Mamdani, the presumptive winner of the Democratic primary for mayor of New York City.

Washington cherry growers struggle to find pickers (Thomas Clouse/Spokesman.com)
https://www.spokesman.com/stories/2025/jun/18/washington-cherry-growers-struggle-to-find-pickers/
http://www.memeorandum.com/250619/p117#a250619p117

SV3.3B: A Sports Video Understanding Model for Action Recognition
Sai Varun Kodathala, Yashwanth Reddy Vutukoori, Rakesh Vunnam
https://arxiv.org/abs/2507.17844 https://

SV3.3B: A Sports Video Understanding Model for Action Recognition
This paper addresses the challenge of automated sports video analysis, which has traditionally been limited by computationally intensive models requiring server-side processing and lacking fine-grained understanding of athletic movements. Current approaches struggle to capture the nuanced biomechanical transitions essential for meaningful sports analysis, often missing critical phases like preparation, execution, and follow-through that occur within seconds. To address these limitations, we int…

Just had a video call with @… from Gaza. Like every family there, they need your help to survive.
Our governments have failed us, we are the only ones who can help. Your donations go directly to keeping families like Aseel’s alive as they struggle to survive Israel’s genocide of the Palestinian people.
Please help Aseel and her family if you can.

Help Sehwel family with their medical treatment
I'm Joe in the UK, I've been in touch with Aseel from the Sehwel family for over a year now and have been following their difficult struggle to afford medication, shelter and food in Gaza. I'm creating this Chuffed campaign for the family to help afford these things and hopefully help them get out of Gaza when the opportunity arises. Here's Aseel's writing:

CodeMorph: Mitigating Data Leakage in Large Language Model Assessment
Hongzhou Rao, Yanjie Zhao, Wenjie Zhu, Ling Xiao, Meizhen Wang, Haoyu Wang
https://arxiv.org/abs/2506.17627

CodeMorph: Mitigating Data Leakage in Large Language Model Assessment
Concerns about benchmark leakage in large language models for code (Code LLMs) have raised issues of data contamination and inflated evaluation metrics. The diversity and inaccessibility of many training datasets make it difficult to prevent data leakage entirely, even with time lag strategies. Consequently, generating new datasets through code perturbation has become essential. However, existing methods often fail to produce complex and diverse variations, struggle with complex cross-file depe…

T-CPDL: A Temporal Causal Probabilistic Description Logic for Developing Logic-RAG Agent
Hong Qing Yu
https://arxiv.org/abs/2506.18559 https://

T-CPDL: A Temporal Causal Probabilistic Description Logic for Developing Logic-RAG Agent
Large language models excel at generating fluent text but frequently struggle with structured reasoning involving temporal constraints, causal relationships, and probabilistic reasoning. To address these limitations, we propose Temporal Causal Probabilistic Description Logic (T-CPDL), an integrated framework that extends traditional Description Logic with temporal interval operators, explicit causal relationships, and probabilistic annotations. We present two distinct variants of T-CPDL: one ca…

SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, Taewhan Kim, Dong-Jin Kim
https://arxiv.org/abs/2507.18632 https://

SIDA: Synthetic Image Driven Zero-shot Domain Adaptation
Zero-shot domain adaptation is a method for adapting a model to a target domain without utilizing target domain image data. To enable adaptation without target images, existing studies utilize CLIP's embedding space and text description to simulate target-like style features. Despite the previous achievements in zero-shot domain adaptation, we observe that these text-driven methods struggle to capture complex real-world variations and significantly increase adaptation time due to their alignmen…

MAARTA:Multi-Agentic Adaptive Radiology Teaching Assistant
Akash Awasthi, Brandon V. Chang, Anh M. Vu, Ngan Le, Rishi Agrawal, Zhigang Deng, Carol Wu, Hien Van Nguyen
https://arxiv.org/abs/2506.17320

MAARTA:Multi-Agentic Adaptive Radiology Teaching Assistant
Radiology students often struggle to develop perceptual expertise due to limited expert mentorship time, leading to errors in visual search and diagnostic interpretation. These perceptual errors, such as missed fixations, short dwell times, or misinterpretations, are not adequately addressed by current AI systems, which focus on diagnostic accuracy but fail to explain how and why errors occur. To address this gap, we introduce MAARTA (Multi-Agentic Adaptive Radiology Teaching Assistant), a mult…

A Learning-based Domain Decomposition Method
Rui Wu, Nikola Kovachki, Burigede Liu
https://arxiv.org/abs/2507.17328 https://arxiv.org…

A Learning-based Domain Decomposition Method
Recent developments in mechanical, aerospace, and structural engineering have driven a growing need for efficient ways to model and analyse structures at much larger and more complex scales than before. While established numerical methods like the Finite Element Method remain reliable, they often struggle with computational cost and scalability when dealing with large and geometrically intricate problems. In recent years, neural network-based methods have shown promise because of their ability …

AI-Generated Song Detection via Lyrics Transcripts
Markus Frohmann, Elena V. Epure, Gabriel Meseguer-Brocal, Markus Schedl, Romain Hennequin
https://arxiv.org/abs/2506.18488

AI-Generated Song Detection via Lyrics Transcripts
The recent rise in capabilities of AI-based music generation tools has created an upheaval in the music industry, necessitating the creation of accurate methods to detect such AI-generated content. This can be done using audio-based detectors; however, it has been shown that they struggle to generalize to unseen generators or when the audio is perturbed. Furthermore, recent work used accurate and cleanly formatted lyrics sourced from a lyrics provider database to detect AI-generated music. Howe…

Towards Robust Fact-Checking: A Multi-Agent System with Advanced Evidence Retrieval
Tam Trinh, Manh Nguyen, Truong-Son Hy
https://arxiv.org/abs/2506.17878 …

Towards Robust Fact-Checking: A Multi-Agent System with Advanced Evidence Retrieval
The rapid spread of misinformation in the digital era poses significant challenges to public discourse, necessitating robust and scalable fact-checking solutions. Traditional human-led fact-checking methods, while credible, struggle with the volume and velocity of online content, prompting the integration of automated systems powered by Large Language Models (LLMs). However, existing automated approaches often face limitations, such as handling complex claims, ensuring source credibility, and m…

HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images
Anilkumar Swamy, Vincent Leroy, Philippe Weinzaepfel, Jean-S\'ebastien Franco, Gr\'egory Rogez
https://arxiv.org/abs/2508.16465

HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images
Hand-object 3D reconstruction has become increasingly important for applications in human-robot interaction and immersive AR/VR experiences. A common approach for object-agnostic hand-object reconstruction from RGB sequences involves a two-stage pipeline: hand-object 3D tracking followed by multi-view 3D reconstruction. However, existing methods rely on keypoint detection techniques, such as Structure from Motion (SfM) and hand-keypoint optimization, which struggle with diverse object geometrie…

Profile-Guided Temporal Prefetching
Mengming Li, Qijun Zhang, Yichuan Gao, Wenji Fang, Yao Lu, Yongqing Ren, Zhiyao Xie
https://arxiv.org/abs/2506.15985 ht…

Profile-Guided Temporal Prefetching
Temporal prefetching shows promise for handling irregular memory access patterns, which are common in data-dependent and pointer-based data structures. Recent studies introduced on-chip metadata storage to reduce the memory traffic caused by accessing metadata from off-chip DRAM. However, existing prefetching schemes struggle to efficiently utilize the limited on-chip storage. An alternative solution, software indirect access prefetching, remains ineffective for optimizing temporal prefetching.…

Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection
Lei Yu, Zhirong Huang, Hang Yuan, Shiqi Cheng, Li Yang, Fengjun Zhang, Chenjie Shen, Jiajia Ma, Jingyuan Zhang, Junyi Lu, Chun Zuo
https://arxiv.org/abs/2506.18245

Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection
Smart contract vulnerability detection remains a major challenge in blockchain security. Existing vulnerability detection methods face two main issues: (1) Existing datasets lack comprehensive coverage and high-quality explanations for preference learning. (2) Large language models (LLMs) often struggle with accurately interpreting specific concepts in smart contract security. Empirical analysis shows that even after continual pre-training (CPT) and supervised fine-tuning (SFT), LLMs may misint…

Leveraging Extrinsic Dexterity for Occluded Grasping on Grasp Constraining Walls
Keita Kobashi, Masayoshi Tomizuka
https://arxiv.org/abs/2507.14721 https:/…

Leveraging Extrinsic Dexterity for Occluded Grasping on Grasp Constraining Walls
This study addresses the problem of occluded grasping, where primary grasp configurations of an object are not available due to occlusion with environment. Simple parallel grippers often struggle with such tasks due to limited dexterity and actuation constraints. Prior works have explored object pose reorientation such as pivoting by utilizing extrinsic contacts between an object and an environment feature like a wall, to make the object graspable. However, such works often assume the presence …

Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective
Hao Dai, Jagmohan Chauhan
https://arxiv.org/abs/2507.17382 ht…

Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective
Continual Generalized Category Discovery (C-GCD) faces a critical challenge: incrementally learning new classes from unlabeled data streams while preserving knowledge of old classes. Existing methods struggle with catastrophic forgetting, especially when unlabeled data mixes known and novel categories. We address this by analyzing C-GCD's forgetting dynamics through a Bayesian lens, revealing that covariance misalignment between old and new classes drives performance degradation. Building on th…

Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
Shikang Zheng, Liang Feng, Xinyu Wang, Qinming Zhou, Peiliang Cai, Chang Zou, Jiacheng Liu, Yuqi Lin, Junjie Chen, Yue Ma, Linfeng Zhang
https://arxiv.org/abs/2508.16211

Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
Diffusion Transformers (DiTs) have demonstrated exceptional performance in high-fidelity image and video generation. To reduce their substantial computational costs, feature caching techniques have been proposed to accelerate inference by reusing hidden representations from previous timesteps. However, current methods often struggle to maintain generation quality at high acceleration ratios, where prediction errors increase sharply due to the inherent instability of long-step forecasting. In th…

LLM-Enhanced Reranking for Complementary Product Recommendation
Zekun Xu, Yudi Zhang
https://arxiv.org/abs/2507.16237 https://arxiv.o…

LLM-Enhanced Reranking for Complementary Product Recommendation
Complementary product recommendation, which aims to suggest items that are used together to enhance customer value, is a crucial yet challenging task in e-commerce. While existing graph neural network (GNN) approaches have made significant progress in capturing complex product relationships, they often struggle with the accuracy-diversity tradeoff, particularly for long-tail items. This paper introduces a model-agnostic approach that leverages Large Language Models (LLMs) to enhance the reranki…

Democrats face challenge in countering Trump on crime (Amie Parnes/The Hill)
https://thehill.com/homenews/administration/5455349-democrats-struggle-crime-response/amp/
http://www.memeorandum.com/250818/p68#a250818p68

TrajSceneLLM: A Multimodal Perspective on Semantic GPS Trajectory Analysis
Chunhou Ji, Qiumeng Li
https://arxiv.org/abs/2506.16401 https://

TrajSceneLLM: A Multimodal Perspective on Semantic GPS Trajectory Analysis
GPS trajectory data reveals valuable patterns of human mobility and urban dynamics, supporting a variety of spatial applications. However, traditional methods often struggle to extract deep semantic representations and incorporate contextual map information. We propose TrajSceneLLM, a multimodal perspective for enhancing semantic understanding of GPS trajectories. The framework integrates visualized map images (encoding spatial context) and textual descriptions generated through LLM reasoning (…

Reinforcement Learning in hyperbolic space for multi-step reasoning
Tao Xu, Dung-Yang Lee, Momiao Xiong
https://arxiv.org/abs/2507.16864 https://

Reinforcement Learning in hyperbolic space for multi-step reasoning
Multi-step reasoning is a fundamental challenge in artificial intelligence, with applications ranging from mathematical problem-solving to decision-making in dynamic environments. Reinforcement Learning (RL) has shown promise in enabling agents to perform multi-step reasoning by optimizing long-term rewards. However, conventional RL methods struggle with complex reasoning tasks due to issues such as credit assignment, high-dimensional state representations, and stability concerns. Recent advanc…

Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing
Kai Huang, Jian Zhang, Xiaofei Xie, Chunyang Chen
https://arxiv.org/abs/2506.16136

Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing
Large language model-(LLM) based automated program repair (APR) techniques have shown promising results in resolving real-world GitHub issue tasks. Existing APR systems are primarily evaluated in unimodal settings (e.g., SWE-bench). However, these autonomous systems struggle to resolve multimodal problem scenarios (e.g., SWE-bench M) due to limitations in interpreting and leveraging visual information. In multimodal scenarios, LLMs need to rely on visual information in the graphical user interf…

Mag-Match: Magnetic Vector Field Features for Map Matching and Registration
William McDonald, Cedric Le Gentil, Jennifer Wakulicz, Teresa Vidal-Calleja
https://arxiv.org/abs/2508.15300

Mag-Match: Magnetic Vector Field Features for Map Matching and Registration
Map matching and registration are essential tasks in robotics for localisation and integration of multi-session or multi-robot data. Traditional methods rely on cameras or LiDARs to capture visual or geometric information but struggle in challenging conditions like smoke or dust. Magnetometers, on the other hand, detect magnetic fields, revealing features invisible to other sensors and remaining robust in such environments. In this paper, we introduce Mag-Match, a novel method for extracting an…

TComQA: Extracting Temporal Commonsense from Text
Lekshmi R Nair, Arun Sankar, Koninika Pal
https://arxiv.org/abs/2508.15274 https://arxiv.org/pdf/2508.152…

TComQA: Extracting Temporal Commonsense from Text
Understanding events necessitates grasping their temporal context, which is often not explicitly stated in natural language. For example, it is not a trivial task for a machine to infer that a museum tour may last for a few hours, but can not take months. Recent studies indicate that even advanced large language models (LLMs) struggle in generating text that require reasoning with temporal commonsense due to its infrequent explicit mention in text. Therefore, automatically mining temporal commo…

ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning
Hao Dai, Chong Tang, Jagmohan Chauhan
https://arxiv.org/abs/2507.17368

ViRN: Variational Inference and Distribution Trilateration for Long-Tailed Continual Representation Learning
Continual learning (CL) with long-tailed data distributions remains a critical challenge for real-world AI systems, where models must sequentially adapt to new classes while retaining knowledge of old ones, despite severe class imbalance. Existing methods struggle to balance stability and plasticity, often collapsing under extreme sample scarcity. To address this, we propose ViRN, a novel CL framework that integrates variational inference (VI) with distributional trilateration for robust long-t…

Semantic Scaffolding: Augmenting Textual Structures with Domain-Specific Groupings for Accessible Data Exploration
Jonathan Zong, Isabella Pedraza Pineros, Mengzhu Katie Chen, Daniel Hajas, Arvind Satyanarayan
https://arxiv.org/abs/2506.15883

Semantic Scaffolding: Augmenting Textual Structures with Domain-Specific Groupings for Accessible Data Exploration
Drawing connections between interesting groupings of data and their real-world meaning is an important, yet difficult, part of encountering a new dataset. A lay reader might see an interesting visual pattern in a chart but lack the domain expertise to explain its meaning. Or, a reader might be familiar with a real-world concept but struggle to express it in terms of a dataset's fields. In response, we developed semantic scaffolding, a technique for using domain-specific information from large l…

“Solidarity activities at the global level should be strategic and impactful. They should focus on disrupting all components of the supply chain that benefit the Israeli occupation in general and settler colonialism in particular. This means citizens around the world in different sectors of society can contribute to the struggle for Palestine as both producers and consumers by heeding the call to boycott and divest from Israel.
Direct actions from the working class are crucial. Workers…

Israel is proceeding with annexation, and there is only one way to stop it
Global grassroots organising is the only way to challenge Israel and its plan to legalise the theft of Palestinian land.

Adaptive Anomaly Detection in Evolving Network Environments
Ehssan Mousavipour, Andrey Dimanchev, Majid Ghaderi
https://arxiv.org/abs/2508.15100 https://ar…

Adaptive Anomaly Detection in Evolving Network Environments
Distribution shift, a change in the statistical properties of data over time, poses a critical challenge for deep learning anomaly detection systems. Existing anomaly detection systems often struggle to adapt to these shifts. Specifically, systems based on supervised learning require costly manual labeling, while those based on unsupervised learning rely on clean data, which is difficult to obtain, for shift adaptation. Both of these requirements are challenging to meet in practice. In this pa…

This piece was created while the apartheid government of South Africa was forcibly removing Coloured families from their homes as part of the destruction of District Six.
#mannenberg #southafrica #amf

Abdullah Ibrahim - Mannenberg - African Music Forum
Abdullah Ibrahim - Mannenberg - The instrumental later became identified with the struggle against apartheid in South Africa.

DiagECG: An LLM-Driven Framework for Diagnostic Reasoning via Discretized ECG Tokenization
Jinning Yang, Wen Shi
https://arxiv.org/abs/2508.15338 https://a…

DiagECG: An LLM-Driven Framework for Diagnostic Reasoning via Discretized ECG Tokenization
Electrocardiography plays a central role in cardiovascular diagnostics, yet existing automated approaches often struggle to generalize across clinical tasks and offer limited support for open-ended reasoning. We present DiagECG, a novel framework that integrates time-series and language modeling by enabling large language models to process 12-lead ECG signals for clinical text generation tasks. Our approach discretizes continuous ECG embeddings into symbolic tokens using a lead-independent enco…

Input Reduction Enhanced LLM-based Program Repair
Boyang Yang, Luyao Ren, Xin Yin, Jiadong Ren, Haoye Tian, Shunfu Jin
https://arxiv.org/abs/2507.15251 htt…

Input Reduction Enhanced LLM-based Program Repair
Large Language Models (LLMs) have shown great potential in Automated Program Repair (APR). Test inputs, being crucial for reasoning the root cause of failures, are always included in the prompt for LLM-based APR. Unfortunately, LLMs struggle to retain key information in long prompts. When the test inputs are extensive in the prompt, this may trigger the "lost-in-the-middle" issue, compromising repair performance. To address this, we propose ReduceFix, an LLM-based APR approach with a built-in c…

Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance
Yufei He, Ruoyu Li, Alex Chen, Yue Liu, Yulin Chen, Yuan Sui, Cheng Chen, Yi Zhu, Luca Luo, Frank Yang, Bryan Hooi
https://arxiv.org/abs/2507.17131

Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance
Large language model (LLM) agents often struggle in environments where rules and required domain knowledge frequently change, such as regulatory compliance and user risk screening. Current approaches, like offline fine-tuning and standard prompting, are insufficient because they cannot effectively adapt to new knowledge during actual operation. To address this limitation, we propose the Adaptive Reflective Interactive Agent (ARIA), an LLM agent framework designed specifically to continuously le…

See it. Say it. Sorted: Agentic System for Compositional Diagram Generation
Hantao Zhang, Jingyang Liu, Ed Li
https://arxiv.org/abs/2508.15222 https://arxi…

See it. Say it. Sorted: Agentic System for Compositional Diagram Generation
We study sketch-to-diagram generation: converting rough hand sketches into precise, compositional diagrams. Diffusion models excel at photorealism but struggle with the spatial precision, alignment, and symbolic structure required for flowcharts. We introduce See it. Say it. Sorted., a training-free agentic system that couples a Vision-Language Model (VLM) with Large Language Models (LLMs) to produce editable Scalable Vector Graphics (SVG) programs. The system runs an iterative loop in which a …

Met$^2$Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems
Shaohan Li, Hao Yang, Min Chen, Xiaolin Qin
https://arxiv.org/abs/2507.17189

Met$^2$Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems
The increasing frequency of extreme weather events due to global climate change urges accurate weather prediction. Recently, great advances have been made by the \textbf{end-to-end methods}, thanks to deep learning techniques, but they face limitations of \textit{representation inconsistency} in multivariable integration and struggle to effectively capture the dependency between variables, which is required in complex weather systems. Treating different variables as distinct modalities and appl…

From Bits to Boardrooms: A Cutting-Edge Multi-Agent LLM Framework for Business Excellence
Zihao Wang, Junming Zhang
https://arxiv.org/abs/2508.15447 https://

From Bits to Boardrooms: A Cutting-Edge Multi-Agent LLM Framework for Business Excellence
Large Language Models (LLMs) have shown promising potential in business applications, particularly in enterprise decision support and strategic planning, yet current approaches often struggle to reconcile intricate operational analyses with overarching strategic goals across diverse market environments, leading to fragmented workflows and reduced collaboration across organizational levels. This paper introduces BusiAgent, a novel multi-agent framework leveraging LLMs for advanced decision-makin…

BugScope: Learn to Find Bugs Like Human
Jinyao Guo, Chengpeng Wang, Dominic Deluca, Jinjie Liu, Zhuo Zhang, Xiangyu Zhang
https://arxiv.org/abs/2507.15671 …

BugScope: Learn to Find Bugs Like Human
Detecting software bugs remains a fundamental challenge due to the extensive diversity of real-world defects. Traditional static analysis tools often rely on symbolic workflows, which restrict their coverage and hinder adaptability to customized bugs with diverse anti-patterns. While recent advances incorporate large language models (LLMs) to enhance bug detection, these methods continue to struggle with sophisticated bugs and typically operate within limited analysis contexts. To address these…

Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation
Zixuan Wang, Jinghao Shi, Hanzhong Liang, Xiang Shen, Vera Wen, Zhiqian Chen, Yifan Wu, Zhixin Zhang, Hongyu Xiong
https://arxiv.org/abs/2507.17204

Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation
Effective content moderation is essential for video platforms to safeguard user experience and uphold community standards. While traditional video classification models effectively handle well-defined moderation tasks, they struggle with complicated scenarios such as implicit harmful content and contextual ambiguity. Multimodal large language models (MLLMs) offer a promising solution to these limitations with their superior cross-modal reasoning and contextual understanding. However, two key ch…

HarmonPaint: Harmonized Training-Free Diffusion Inpainting
Ying Li, Xinzhe Li, Yong Du, Yangyang Xu, Junyu Dong, Shengfeng He
https://arxiv.org/abs/2507.16732

HarmonPaint: Harmonized Training-Free Diffusion Inpainting
Existing inpainting methods often require extensive retraining or fine-tuning to integrate new content seamlessly, yet they struggle to maintain coherence in both structure and style between inpainted regions and the surrounding background. Motivated by these limitations, we introduce HarmonPaint, a training-free inpainting framework that seamlessly integrates with the attention mechanisms of diffusion models to achieve high-quality, harmonized image inpainting without any form of training. By …

Synthetic Data Matters: Re-training with Geo-typical Synthetic Labels for Building Detection
Shuang Song, Yang Tang, Rongjun Qin
https://arxiv.org/abs/2507.16657

Synthetic Data Matters: Re-training with Geo-typical Synthetic Labels for Building Detection
Deep learning has significantly advanced building segmentation in remote sensing, yet models struggle to generalize on data of diverse geographic regions due to variations in city layouts and the distribution of building types, sizes and locations. However, the amount of time-consuming annotated data for capturing worldwide diversity may never catch up with the demands of increasingly data-hungry models. Thus, we propose a novel approach: re-training models at test time using synthetic data tai…

Language-Guided Tuning: Enhancing Numeric Optimization with Textual Feedback
Yuxing Lu, Yucheng Hu, Nan Sun, Xukai Zhao
https://arxiv.org/abs/2508.15757 https://

Language-Guided Tuning: Enhancing Numeric Optimization with Textual Feedback
Configuration optimization remains a critical bottleneck in machine learning, requiring coordinated tuning across model architecture, training strategy, feature engineering, and hyperparameters. Traditional approaches treat these dimensions independently and lack interpretability, while recent automated methods struggle with dynamic adaptability and semantic reasoning about optimization decisions. We introduce Language-Guided Tuning (LGT), a novel framework that employs multi-agent Large Langua…

RDMA: Cost Effective Agent-Driven Rare Disease Discovery within Electronic Health Record Systems
John Wu, Adam Cross, Jimeng Sun
https://arxiv.org/abs/2507.15867

RDMA: Cost Effective Agent-Driven Rare Disease Discovery within Electronic Health Record Systems
Rare diseases affect 1 in 10 Americans, yet standard ICD coding systems fail to capture these conditions in electronic health records (EHR), leaving crucial information buried in clinical notes. Current approaches struggle with medical abbreviations, miss implicit disease mentions, raise privacy concerns with cloud processing, and lack clinical reasoning abilities. We present Rare Disease Mining Agents (RDMA), a framework that mirrors how medical experts identify rare disease patterns in EHR. R…

HOComp: Interaction-Aware Human-Object Composition
Dong Liang, Jinyuan Jia, Yuhao Liu, Rynson W. H. Lau
https://arxiv.org/abs/2507.16813 https://

HOComp: Interaction-Aware Human-Object Composition
While existing image-guided composition methods may help insert a foreground object onto a user-specified region of a background image, achieving natural blending inside the region with the rest of the image unchanged, we observe that these existing methods often struggle in synthesizing seamless interaction-aware compositions when the task involves human-object interactions. In this paper, we first propose HOComp, a novel approach for compositing a foreground object onto a human-centric backgr…

First RAG, Second SEG: A Training-Free Paradigm for Camouflaged Object Detection
Wutao Liu, YiDan Wang, Pan Gao
https://arxiv.org/abs/2508.15313 https://ar…

First RAG, Second SEG: A Training-Free Paradigm for Camouflaged Object Detection
Camouflaged object detection (COD) poses a significant challenge in computer vision due to the high similarity between objects and their backgrounds. Existing approaches often rely on heavy training and large computational resources. While foundation models such as the Segment Anything Model (SAM) offer strong generalization, they still struggle to handle COD tasks without fine-tuning and require high-quality prompts to yield good performance. However, generating such prompts manually is costly…

Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption
Keneni W. Tesema, Lyndon Hill, Mark W. Jones, Gary K. L. Tam
https://arxiv.org/abs/2507.16743

Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption
Point cloud completion is crucial for 3D computer vision tasks in autonomous driving, augmented reality, and robotics. However, obtaining clean and complete point clouds from real-world environments is challenging due to noise and occlusions. Consequently, most existing completion networks -- trained on synthetic data -- struggle with real-world degradations. In this work, we tackle the problem of completing and denoising highly corrupted partial point clouds affected by multiple simultaneous d…

Beyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks
Saman Yazdannik, Morteza Tayefi, Shamim Sanisales
https://arxiv.org/abs/2508.14536 https://arxiv.or…

Beyond ReLU: Chebyshev-DQN for Enhanced Deep Q-Networks
The performance of Deep Q-Networks (DQN) is critically dependent on the ability of its underlying neural network to accurately approximate the action-value function. Standard function approximators, such as multi-layer perceptrons, may struggle to efficiently represent the complex value landscapes inherent in many reinforcement learning problems. This paper introduces a novel architecture, the Chebyshev-DQN (Ch-DQN), which integrates a Chebyshev polynomial basis into the DQN framework to create…

Multi-Object Sketch Animation with Grouping and Motion Trajectory Priors
Guotao Liang, Juncheng Hu, Ximing Xing, Jing Zhang, Qian Yu
https://arxiv.org/abs/2508.15535 https://

Multi-Object Sketch Animation with Grouping and Motion Trajectory Priors
We introduce GroupSketch, a novel method for vector sketch animation that effectively handles multi-object interactions and complex motions. Existing approaches struggle with these scenarios, either being limited to single-object cases or suffering from temporal inconsistency and poor generalization. To address these limitations, our method adopts a two-stage pipeline comprising Motion Initialization and Motion Refinement. In the first stage, the input sketch is interactively divided into seman…

Spiking Variational Graph Representation Inference for Video Summarization
Wenrui Li, Wei Han, Liang-Jian Deng, Ruiqin Xiong, Xiaopeng Fan
https://arxiv.org/abs/2508.15389 https…

Spiking Variational Graph Representation Inference for Video Summarization
With the rise of short video content, efficient video summarization techniques for extracting key information have become crucial. However, existing methods struggle to capture the global temporal dependencies and maintain the semantic coherence of video content. Additionally, these methods are also influenced by noise during multi-channel feature fusion. We propose a Spiking Variational Graph (SpiVG) Network, which enhances information density and reduces computational complexity. First, we de…

BLIPs: Bayesian Learned Interatomic Potentials
Dario Coscia, Pim de Haan, Max Welling
https://arxiv.org/abs/2508.14022 https://arxiv.org/pdf/2508.14022

BLIPs: Bayesian Learned Interatomic Potentials
Machine Learning Interatomic Potentials (MLIPs) are becoming a central tool in simulation-based chemistry. However, like most deep learning models, MLIPs struggle to make accurate predictions on out-of-distribution data or when trained in a data-scarce regime, both common scenarios in simulation-based chemistry. Moreover, MLIPs do not provide uncertainty estimates by construction, which are fundamental to guide active learning pipelines and to ensure the accuracy of simulation results compared …