Tootfinder

The Daily Star drops its page three with pictures of scantily dressed women as part of a print and online redesign, with a new strapline "News with a wink" (Charlotte Tobitt/Press Gazette)
https://pressgazette.co.uk/publishers/

Daily Star drops page three pictures of scantily dressed women in redesign
The Daily Star has ditched page three models amid a wider redesign which includes a new masthead, new website/app platforms and new strapline

これ読むといいんじゃないかな。うえのさんの。
--
二つのクリスマス. ——何かを「待ちのぞむ」ということ | by ueno | Medium
https://oryzivora.page/二つのクリスマス-750d0b08d274?gi=705df5f6d027

Trump’s appeal of EJ Carroll’s $83.3 million defamation verdict against him is set for oral argument June 24
Trump & DOJ have jointly moved to postpone
This case involves alleged defamations in 2019, when Trump was president.
At various times Trump has invoked, and lost,
both presidential immunity and "Westfall immunity".
The Westfall Act says that the US is responsible for any govt employee’s tort within the scope of his/her employment

This https://arxiv.org/abs/2506.02475 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Comba: Improving Nonlinear RNNs with Closed-loop Control
Recent efficient sequence modeling methods such as Gated DeltaNet, TTT, and RWKV-7 have achieved performance improvements by supervising the recurrent memory management through Delta learning rule. Unlike previous state-space models (e.g., Mamba) and gated linear attentions (e.g., GLA), these models introduce interactions between the recurrent state and the key vector, resulting in a nonlinear recursive structure. In this paper, we first introduce the concept of Nonlinear RNNs with a comprehens…

This https://arxiv.org/abs/2506.06266 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Cartridges: Lightweight and general-purpose long context representations via self-study
Large language models are often used to answer queries grounded in large text corpora (e.g. codebases, legal documents, or chat histories) by placing the entire corpus in the context window and leveraging in-context learning (ICL). Although current models support contexts of 100K-1M tokens, this setup is costly to serve because the memory consumption of the KV cache scales with input length. We explore an alternative: training a smaller KV cache offline on each corpus. At inference time, we loa…

Added a link to nsf-iaa.org with some autistic flair: #Anarchism #Syndicalism

[2025-06-11 Wed (UTC), 1 new article found for math.CT Category Theory]
toXiv_bot_toot

@… @… on my site I linked the image to a `/uses/` page that had the attribution (if that helps!)

For my next modern culture and media studies work, I'd like to use "THE SIMPLE NEW SOCIO-ECONOMICGEOPOLITICALBIO-HISTORICAL APPROACH" (TSR 1987)
(The eighties were a very weird time, y'all.)
(I found this in WCA #26, ZODIAC ATTACK)

This https://arxiv.org/abs/2506.06155 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

A Novel Large-scale Crop Dataset and Dual-stream Transformer Method for Fine-grained Hierarchical Crop Classification from Integrated Hyperspectral EnMAP Data and Multispectral Sentinel-2 Time Series
Fine-grained crop classification is crucial for precision agriculture and food security monitoring. It requires simultaneous capture of both phenological dynamics (obtained from multi-temporal satellite data like Sentinel-2) and subtle spectral variations (demanding nanometer-scale spectral resolution from hyperspectral imagery). Research combining these two modalities remains scarce currently due to challenges in hyperspectral data acquisition and crop types annotation costs. To address these …

edit_wikibooks: Wikipedia book edits (2010)
Two bipartite user-page networks extracted from Wikipedia, about books. A user connects to a page if that user edited that page. Edits (edges) are timestamped. Edge weights represent counts of the number of edits.
This network has 971 nodes and 1487 edges.
Tags: Informational, Web graph, Multigraph, Timestamps

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new/
[5/5]:
AnnaAgent: Dynamic Evolution Agent System with Multi-Session Memory for Realistic Seeker Simulation

This https://arxiv.org/abs/2503.24078 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLO_…

A Complete Mental Temporal Logic for Intelligent Agent
In this paper, we present a complete mental temporal logic, called BPICTL, which generalizes CTL by introducing mental modalities. A sound and complete inference system of BPICTL is given. We prove the finite model property of BPICTL. Furthermore, we present a model checking algorithm for BPICTL.

This https://arxiv.org/abs/2506.06091 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

MIRIAD: Augmenting LLMs with millions of medical query-response pairs
LLMs are bound to transform healthcare with advanced decision support and flexible chat assistants. However, LLMs are prone to generate inaccurate medical content. To ground LLMs in high-quality medical knowledge, LLMs have been equipped with external knowledge via RAG, where unstructured medical knowledge is split into small text chunks that can be selectively retrieved and integrated into the LLMs context. Yet, existing RAG pipelines rely on raw, unstructured medical text, which can be noisy,…

02:13—Good Night #Fediverse! 😴💤
I added some more autistic flare at #Night

This https://arxiv.org/abs/2506.06278 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Distillation Robustifies Unlearning
Current LLM unlearning methods are not robust: they can be reverted easily with a few steps of finetuning. This is true even for the idealized unlearning method of training to imitate an oracle model that was never exposed to unwanted information, suggesting that output-based finetuning is insufficient to achieve robust unlearning. In a similar vein, we find that training a randomly initialized student to imitate an unlearned model transfers desired behaviors while leaving undesired capabilitie…

This https://arxiv.org/abs/2506.05660 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

TissUnet: Improved Extracranial Tissue and Cranium Segmentation for Children through Adulthood
Extracranial tissues visible on brain magnetic resonance imaging (MRI) may hold significant value for characterizing health conditions and clinical decision-making, yet they are rarely quantified. Current tools have not been widely validated, particularly in settings of developing brains or underlying pathology. We present TissUnet, a deep learning model that segments skull bone, subcutaneous fat, and muscle from routine three-dimensional T1-weighted MRI, with or without contrast enhancement. T…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new/
[4/5]:
Evolutionary Policy Optimization
https://arxiv.o…

At various times Trump has invoked, and lost, both presidential immunity and Westfall immunity.
The Westfall Act says that the US is responsible for any govt employee’s tort within the scope of his/her employment.
https://skywriter.blue/pages/did:plc:v

This https://arxiv.org/abs/2506.05850 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Cross-lingual Collapse: How Language-Centric Foundation Models Shape Reasoning in Large Language Models
We identify \textbf{Cross-lingual Collapse}, a systematic drift in which the chain-of-thought (CoT) of a multilingual language model reverts to its dominant pre-training language even when the prompt is expressed in a different language. Recent large language models (LLMs) with reinforcement learning with verifiable reward (RLVR) have achieved strong logical reasoning performances by exposing their intermediate reasoning traces, giving rise to large reasoning models (LRMs). However, the mechani…

This https://arxiv.org/abs/2506.06105 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Text-to-LoRA: Instant Transformer Adaption
While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of the underlying model. Fine-tuning techniques enable practitioners to adapt foundation models for many new applications but require expensive and lengthy training while being notably sensitive to hyper-parameter choices. To overcome these limitations, we introduce Text-to-LoRA (T2…

This https://arxiv.org/abs/2506.05317 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimation
Neural rendering has made significant strides in 3D reconstruction and novel view synthesis. With the integration with physics, it opens up new applications. The inverse problem of estimating physics from visual data, however, still remains challenging, limiting its effectiveness for applications like physically accurate digital twin creation in robotics and XR. Existing methods that incorporate physics into neural rendering frameworks typically require dense multi-view videos as input, making …

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new/
[3/5]:
From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models

The fact that most people—even the punditocracy—seem to willfully not remember who was president in 2020 explains a lot of current political discourse on numerous subjects
https://skywriter.blue/pages/did:plc:swgxwbir4rrimj57pf75jckf/post/3lrbbdbrl…

This https://arxiv.org/abs/2506.05960 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

AQUATIC-Diff: Additive Quantization for Truly Tiny Compressed Diffusion Models
Significant investments have been made towards the commodification of diffusion models for generation of diverse media. Their mass-market adoption is however still hobbled by the intense hardware resource requirements of diffusion model inference. Model quantization strategies tailored specifically towards diffusion models have been useful in easing this burden, yet have generally explored the Uniform Scalar Quantization (USQ) family of quantization methods. In contrast, Vector Quantization (VQ…

This https://arxiv.org/abs/2506.05096 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Astraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers
Video diffusion transformers (vDiTs) have made impressive progress in text-to-video generation, but their high computational demands present major challenges for practical deployment. While existing acceleration methods reduce workload at various granularities, they often rely on heuristics, limiting their applicability. We introduce ASTRAEA, an automatic framework that searches for near-optimal configurations for vDiT-based video generation. At its core, ASTRAEA proposes a lightweight token …

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new/
[2/5]:
Structuring Concept Space with the Musical Circle of Fifths by Utilizing Music Grammar Based Acti...

This https://arxiv.org/abs/2506.05675 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Zero-Shot Event Causality Identification via Multi-source Evidence Fuzzy Aggregation with Large Language Models
Event Causality Identification (ECI) aims to detect causal relationships between events in textual contexts. Existing ECI models predominantly rely on supervised methodologies, suffering from dependence on large-scale annotated data. Although Large Language Models (LLMs) enable zero-shot ECI, they are prone to causal hallucination-erroneously establishing spurious causal links. To address these challenges, we propose MEFA, a novel zero-shot framework based on Multi-source Evidence Fuzzy Aggrega…

This https://arxiv.org/abs/2506.05831 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Heartcare Suite: Multi-dimensional Understanding of ECG with Raw Multi-lead Signal Modeling
We present Heartcare Suite, a multimodal comprehensive framework for finegrained electrocardiogram (ECG) understanding. It comprises three key components: (i) Heartcare-220K, a high-quality, structured, and comprehensive multimodal ECG dataset covering essential tasks such as disease diagnosis, waveform morphology analysis, and rhythm interpretation. (ii) Heartcare-Bench, a systematic and multi-dimensional benchmark designed to evaluate diagnostic intelligence and guide the optimization of Medi…

This https://arxiv.org/abs/2506.05008 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Structure-Aware Radar-Camera Depth Estimation
Monocular depth estimation aims to determine the depth of each pixel from an RGB image captured by a monocular camera. The development of deep learning has significantly advanced this field by facilitating the learning of depth features from some well-annotated datasets \cite{Geiger_Lenz_Stiller_Urtasun_2013,silberman2012indoor}. Eigen \textit{et al.} \cite{eigen2014depth} first introduce a multi-scale fusion network for depth regression. Following this, subsequent improvements have come from r…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new/
[1/5]:
FREIDA: A Framework for developing quantitative agent based models based on qualitative expert kn...

This https://arxiv.org/abs/2506.05339 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Flattery, Fluff, and Fog: Diagnosing and Mitigating Idiosyncratic Biases in Preference Models
Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on features like length, structure, and style, leading to issues like reward hacking and unreliable evaluations. Evidence suggests these biases originate in artifacts in human training data. In this work, we systematically investigate the relationship between tra…

This https://arxiv.org/abs/2506.05678 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Numerical Investigation of Sequence Modeling Theory using Controllable Memory Functions
The evolution of sequence modeling architectures, from recurrent neural networks and convolutional models to Transformers and structured state-space models, reflects ongoing efforts to address the diverse temporal dependencies inherent in sequential data. Despite this progress, systematically characterizing the strengths and limitations of these architectures remains a fundamental challenge.In this work, we propose a synthetic benchmarking framework to evaluate how effectively different sequenc…

This https://arxiv.org/abs/2506.04668 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Feature-Based Lie Group Transformer for Real-World Applications
The main goal of representation learning is to acquire meaningful representations from real-world sensory inputs without supervision. Representation learning explains some aspects of human development. Various neural network (NN) models have been proposed that acquire empirically good representations. However, the formulation of a good representation has not been established. We recently proposed a method for categorizing changes between a pair of sensory inputs. A unique feature of this approa…

This https://arxiv.org/abs/2506.05142 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Do Large Language Models Judge Error Severity Like Humans?
Large Language Models (LLMs) are increasingly used as automated evaluators in natural language generation, yet it remains unclear whether they can accurately replicate human judgments of error severity. In this study, we systematically compare human and LLM assessments of image descriptions containing controlled semantic errors. We extend the experimental framework of van Miltenburg et al. (2020) to both unimodal (text-only) and multimodal (text + image) settings, evaluating four error types: a…

This https://arxiv.org/abs/2506.05673 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Peer-Ranked Precision: Creating a Foundational Dataset for Fine-Tuning Vision Models from DataSeeds' Annotated Imagery
The development of modern Artificial Intelligence (AI) models, particularly diffusion-based models employed in computer vision and image generation tasks, is undergoing a paradigmatic shift in development methodologies. Traditionally dominated by a "Model Centric" approach, in which performance gains were primarily pursued through increasingly complex model architectures and hyperparameter optimization, the field is now recognizing a more nuanced "Data-Centric" approach. This emergent framework…

This https://arxiv.org/abs/2506.03988 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors
AI-generated images have reached a quality level at which humans are incapable of reliably distinguishing them from real images. To counteract the inherent risk of fraud and disinformation, the detection of AI-generated images is a pressing challenge and an active research topic. While many of the presented methods claim to achieve high detection accuracy, they are usually evaluated under idealized conditions. In particular, the adversarial robustness is often neglected, potentially due to a la…

This https://arxiv.org/abs/2506.04929 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

ConECT Dataset: Overcoming Data Scarcity in Context-Aware E-Commerce MT
Neural Machine Translation (NMT) has improved translation by using Transformer-based models, but it still struggles with word ambiguity and context. This problem is especially important in domain-specific applications, which often have problems with unclear sentences or poor data quality. Our research explores how adding information to models can improve translations in the context of e-commerce data. To this end we create ConECT -- a new Czech-to-Polish e-commerce product translation dataset c…

This https://arxiv.org/abs/2506.05526 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

On Fitting Flow Models with Large Sinkhorn Couplings
Flow models transform data gradually from one modality (e.g. noise) onto another (e.g. images). Such models are parameterized by a time-dependent velocity field, trained to fit segments connecting pairs of source and target points. When the pairing between source and target points is given, training flow models boils down to a supervised regression problem. When no such pairing exists, as is the case when generating data from noise, training flows is much harder. A popular approach lies in pick…

This https://arxiv.org/abs/2506.03589 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance
Text-video retrieval (TVR) systems often suffer from visual-linguistic biases present in datasets, which cause pre-trained vision-language models to overlook key details. To address this, we propose BiMa, a novel framework designed to mitigate biases in both visual and textual representations. Our approach begins by generating scene elements that characterize each video by identifying relevant entities/objects and activities. For visual debiasing, we integrate these scene elements into the vide…

This https://arxiv.org/abs/2506.04907 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Verbose ListOps (VLO): Beyond Long Context -- Unmasking LLM's Reasoning Blind Spots
Large Language Models (LLMs), whilst great at extracting facts from text, struggle with nested narrative reasoning. Existing long context and multi-hop QA benchmarks inadequately test this, lacking realistic distractors or failing to decouple context length from reasoning complexity, masking a fundamental LLM limitation. We introduce Verbose ListOps, a novel benchmark that programmatically transposes ListOps computations into lengthy, coherent stories. This uniquely forces internal computation …

This https://arxiv.org/abs/2506.05047 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Reliably detecting model failures in deployment without labels
The distribution of data changes over time; models operating operating in dynamic environments need retraining. But knowing when to retrain, without access to labels, is an open challenge since some, but not all shifts degrade model performance. This paper formalizes and addresses the problem of post-deployment deterioration (PDD) monitoring. We propose D3M, a practical and efficient monitoring algorithm based on the disagreement of predictive models, achieving low false positive rates under no…

This https://arxiv.org/abs/2506.02976 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Deep Learning for Retinal Degeneration Assessment: A Comprehensive Analysis of the MARIO AMD Progression Challenge
The MARIO challenge, held at MICCAI 2024, focused on advancing the automated detection and monitoring of age-related macular degeneration (AMD) through the analysis of optical coherence tomography (OCT) images. Designed to evaluate algorithmic performance in detecting neovascular activity changes within AMD, the challenge incorporated unique multi-modal datasets. The primary dataset, sourced from Brest, France, was used by participating teams to train and test their models. The final ranking wa…

This https://arxiv.org/abs/2506.04047 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

On Support Samples of Next Word Prediction
Language models excel in various tasks by making complex decisions, yet understanding the rationale behind these decisions remains a challenge. This paper investigates \emph{data-centric interpretability} in language models, focusing on the next-word prediction task. Using representer theorem, we identify two types of \emph{support samples}-those that either promote or deter specific predictions. Our findings reveal that being a support sample is an intrinsic property, predictable even before t…

This https://arxiv.org/abs/2506.04168 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Horizon Reduction Makes RL Scalable
In this work, we study the scalability of offline reinforcement learning (RL) algorithms. In principle, a truly scalable offline RL algorithm should be able to solve any given problem, regardless of its complexity, given sufficient data, compute, and model capacity. We investigate if and how current offline RL algorithms match up to this promise on diverse, challenging, previously unsolved tasks, using datasets up to 1000x larger than typical offline RL datasets. We observe that despite scaling…

This https://arxiv.org/abs/2506.01933 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models
Spatial intelligence, encompassing 3D reconstruction, perception, and reasoning, is fundamental to applications such as robotics, aerial imaging, and extended reality. A key enabler is the real-time, accurate estimation of core 3D attributes (camera parameters, point clouds, depth maps, and 3D point tracks) from unstructured or streaming imagery. Inspired by the success of large foundation models in language and 2D vision, a new class of end-to-end 3D geometric foundation models (GFMs) has emer…

This https://arxiv.org/abs/2506.03978 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Structured Pruning for Diverse Best-of-N Reasoning Optimization
Model pruning in transformer-based language models, traditionally viewed as a means of achieving computational savings, can enhance the model's reasoning capabilities. In this work, we uncover a surprising phenomenon: the selective pruning of certain attention heads leads to improvements in reasoning performance, particularly on challenging tasks. Motivated by this observation, we propose SPRINT, a novel contrastive learning framework that dynamically selects the optimal head and layer to prune…

This https://arxiv.org/abs/2506.03703 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning-at-Criticality in Large Language Models for Quantum Field Theory and Beyond
Fundamental physics often confronts complex symbolic problems with few guiding exemplars or established principles. While artificial intelligence (AI) offers promise, its typical need for vast datasets to learn from hinders its use in these information-scarce frontiers. We introduce learning at criticality (LaC), a reinforcement learning (RL) scheme that tunes Large Language Models (LLMs) to a sharp learning transition, addressing this information scarcity. At this transition, LLMs achieve peak…

This https://arxiv.org/abs/2506.00978 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

CAPAA: Classifier-Agnostic Projector-Based Adversarial Attack
Projector-based adversarial attack aims to project carefully designed light patterns (i.e., adversarial projections) onto scenes to deceive deep image classifiers. It has potential applications in privacy protection and the development of more robust classifiers. However, existing approaches primarily focus on individual classifiers and fixed camera poses, often neglecting the complexities of multi-classifier systems and scenarios with varying camera poses. This limitation reduces their effecti…

This https://arxiv.org/abs/2506.03038 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective
Reinforcement learning (RL) enhances large language models (LLMs) in complex, long-chain-of-thought (long-CoT) reasoning. The advanced VAPO framework, despite sophisticated mechanisms like Decoupled GAE, theoretically faces fundamental limitations in comprehensively modeling and leveraging deep, long-term value for fine-grained, step-by-step policy guidance in extended reasoning chains. We argue these limitations stem from inherent difficulties in credit assignment, value function representatio…

This https://arxiv.org/abs/2506.03100 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
Retrieval-augmented generation (RAG) has seen many empirical successes in recent years by aiding the LLM with external knowledge. However, its theoretical aspect has remained mostly unexplored. In this paper, we propose the first finite-sample generalization bound for RAG in in-context linear regression and derive an exact bias-variance tradeoff. Our framework views the retrieved texts as query-dependent noisy in-context examples and recovers the classical in-context learning (ICL) and standard…

This https://arxiv.org/abs/2506.00558 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

ViVo: A Dataset for Volumetric VideoReconstruction and Compression
As research on neural volumetric video reconstruction and compression flourishes, there is a need for diverse and realistic datasets, which can be used to develop and validate reconstruction and compression models. However, existing volumetric video datasets lack diverse content in terms of both semantic and low-level features that are commonly present in real-world production pipelines. In this context, we propose a new dataset, ViVo, for VolumetrIc VideO reconstruction and compression. The da…

This https://arxiv.org/abs/2506.02878 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

CoT is Not True Reasoning, It Is Just a Tight Constraint to Imitate: A Theory Perspective
Chain-of-Thought (CoT) prompting has demonstrably enhanced the performance of Large Language Models on tasks requiring multi-step inference. This success has led to widespread claims of emergent reasoning capabilities in these models. In this paper, we present a theoretical counter-perspective: Chain-of-Thought (CoT) does not elicit genuine, abstract reasoning. Instead, we argue that Chain-of-Thought functions as a powerful structural constraint that guides Large Language Models to imitate the …

This https://arxiv.org/abs/2506.02308 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping
Recent advances in multimodal foundation models have achieved state-of-the-art performance across a range of tasks. These breakthroughs are largely driven by new pre-training paradigms that leverage large-scale, unlabeled multimodal data, followed by instruction fine-tuning on curated labeled datasets and high-quality prompts. While there is growing interest in scaling instruction fine-tuning to ever-larger datasets in both quantity and scale, our findings reveal that simply increasing the numb…

This https://arxiv.org/abs/2505.24718 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Reinforcing Video Reasoning with Focused Thinking
Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations persist: 1) they often produce unfocused, verbose reasoning chains that obscure salient spatiotemporal cues and 2) binary rewarding fails to account for partially correct answers, resulting in high reward variance and inefficient learning. In this paper, we propos…

This https://arxiv.org/abs/2506.01495 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

CVC: A Large-Scale Chinese Value Rule Corpus for Value Alignment of Large Language Models
Ensuring that Large Language Models (LLMs) align with mainstream human values and ethical norms is crucial for the safe and sustainable development of AI. Current value evaluation and alignment are constrained by Western cultural bias and incomplete domestic frameworks reliant on non-native rules; furthermore, the lack of scalable, rule-driven scenario generation methods makes evaluations costly and inadequate across diverse cultural contexts. To address these challenges, we propose a hierarchi…

This https://arxiv.org/abs/2506.01790 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

$IF-GUIDE$: Influence Function-Guided Detoxification of LLMs
We study how training data contributes to the emergence of toxic behaviors in large-language models. Most prior work on reducing model toxicity adopts $reactive$ approaches, such as fine-tuning pre-trained (and potentially toxic) models to align them with human values. In contrast, we propose a $proactive$ approach$-$IF-Guide$-$which leverages influence functions to identify harmful tokens within any training data and suppress their impact during training. To this end, we first show that standa…

This https://arxiv.org/abs/2505.24247 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

50 Years of Automated Face Recognition
Over the past 50 years, automated face recognition has evolved from rudimentary, handcrafted systems into sophisticated deep learning models that rival and often surpass human performance. This paper chronicles the history and technological progression of FR, from early geometric and statistical methods to modern deep neural architectures leveraging massive real and AI-generated datasets. We examine key innovations that have shaped the field, including developments in dataset, loss function, ne…

This https://arxiv.org/abs/2506.01348 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Distributionally Robust Learning in Survival Analysis
We introduce an innovative approach that incorporates a Distributionally Robust Learning (DRL) approach into Cox regression to enhance the robustness and accuracy of survival predictions. By formulating a DRL framework with a Wasserstein distance-based ambiguity set, we develop a variant Cox model that is less sensitive to assumptions about the underlying data distribution and more resilient to model misspecification and data perturbations. By leveraging Wasserstein duality, we reformulate the …

This https://arxiv.org/abs/2505.21904 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation
Instance segmentation demands costly per-pixel annotations and large models. We introduce CAST, a semi-supervised knowledge distillation (SSKD) framework that compresses pretrained vision foundation models (VFM) into compact experts using limited labeled and abundant unlabeled data. CAST unfolds in three stages: (1) domain adaptation of the VFM teacher(s) via self-training with contrastive pixel calibration, (2) distillation into a compact student via a unified multi-objective loss that couples…

This https://arxiv.org/abs/2506.00436 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning from Double Positive and Unlabeled Data for Potential-Customer Identification
In this study, we propose a method for identifying potential customers in targeted marketing by applying learning from positive and unlabeled data (PU learning). We consider a scenario in which a company sells a product and can observe only the customers who purchased it. Decision-makers seek to market products effectively based on whether people have loyalty to the company. Individuals with loyalty are those who are likely to remain interested in the company even without additional advertising…

This https://arxiv.org/abs/2505.21036 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy
Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion}, a novel training-free sparse attention method that exploits inherent sparsity nature in visual data to accelerate attention computation while preserving video quality. Specifically, we identify three unique sparse patterns in video generation attention calcu…

This https://arxiv.org/abs/2505.23868 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Noise-Robustness Through Noise: Asymmetric LoRA Adaption with Poisoning Expert
Current parameter-efficient fine-tuning methods for adapting pre-trained language models to downstream tasks are susceptible to interference from noisy data. Conventional noise-handling approaches either rely on laborious data pre-processing or employ model architecture modifications prone to error accumulation. In contrast to existing noise-process paradigms, we propose a noise-robust adaptation method via asymmetric LoRA poisoning experts (LoPE), a novel framework that enhances model robustne…

This https://arxiv.org/abs/2505.20124 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos
Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing benchmarks for video understanding often treat these properties separately or narrowly focus on specific aspects, overlooking the holistic nature of video content. To address this, we introduce TUNA, a temporal-oriented benchmark for fine-grained understanding on dense dynamic videos, with two complementary tasks: captio…

This https://arxiv.org/abs/2505.22772 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Calibrated Value-Aware Model Learning with Stochastic Environment Models
The idea of value-aware model learning, that models should produce accurate value estimates, has gained prominence in model-based reinforcement learning. The MuZero loss, which penalizes a model's value function prediction compared to the ground-truth value function, has been utilized in several prominent empirical works in the literature. However, theoretical investigation into its strengths and weaknesses is limited. In this paper, we analyze the family of value-aware model learning losses, w…

This https://arxiv.org/abs/2505.19111 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Remote Sensing Image Classification with Decoupled Knowledge Distillation
To address the challenges posed by the large number of parameters in existing remote sensing image classification models, which hinder deployment on resource-constrained devices, this paper proposes a lightweight classification method based on knowledge distillation. Specifically, G-GhostNet is adopted as the backbone network, leveraging feature reuse to reduce redundant parameters and significantly improve inference efficiency. In addition, a decoupled knowledge distillation strategy is employ…

This https://arxiv.org/abs/2505.19038 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Turb-L1: Achieving Long-term Turbulence Tracing By Tackling Spectral Bias
Accurately predicting the long-term evolution of turbulence is crucial for advancing scientific understanding and optimizing engineering applications. However, existing deep learning methods face significant bottlenecks in long-term autoregressive prediction, which exhibit excessive smoothing and fail to accurately track complex fluid dynamics. Our extensive experimental and spectral analysis of prevailing methods provides an interpretable explanation for this shortcoming, identifying Spectral …

This https://arxiv.org/abs/2505.18700 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
Recent advances in Visual Language Models (VLMs) have demonstrated exceptional performance in visual reasoning tasks. However, geo-localization presents unique challenges, requiring the extraction of multigranular visual cues from images and their integration with external world knowledge for systematic reasoning. Current approaches to geo-localization tasks often lack robust reasoning mechanisms and explainability, limiting their effectiveness. To address these limitations, we propose the Geo …

This https://arxiv.org/abs/2505.18565 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning Fluid-Structure Interaction Dynamics with Physics-Informed Neural Networks and Immersed Boundary Methods
We introduce neural network architectures that combine physics-informed neural networks (PINNs) with the immersed boundary method (IBM) to solve fluid-structure interaction (FSI) problems. Our approach features two distinct architectures: a Single-FSI network with a unified parameter space, and an innovative Eulerian-Lagrangian network that maintains separate parameter spaces for fluid and structure domains. We study each architecture using standard Tanh and adaptive B-spline activation functio…

This https://arxiv.org/abs/2505.18675 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Can MLLMs Guide Me Home? A Benchmark Study on Fine-Grained Visual Reasoning from Transit Maps
Multimodal large language models (MLLMs) have recently achieved significant progress in visual tasks, including semantic scene understanding and text-image alignment, with reasoning variants enhancing performance on complex tasks involving mathematics and logic. However, their capacity for reasoning tasks involving fine-grained visual understanding remains insufficiently evaluated. To address this gap, we introduce ReasonMap, a benchmark designed to assess the fine-grained visual understanding …

This https://arxiv.org/abs/2505.18344 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Sample Complexity of Diffusion Model Training Without Empirical Risk Minimizer Access
Diffusion models have demonstrated state-of-the-art performance across vision, language, and scientific domains. Despite their empirical success, prior theoretical analyses of the sample complexity suffer from poor scaling with input data dimension or rely on unrealistic assumptions such as access to exact empirical risk minimizers. In this work, we provide a principled analysis of score estimation, establishing a sample complexity bound of $\widetilde{\mathcal{O}}(ε^{-6})$. Our approach lever…

This https://arxiv.org/abs/2505.18668 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

ChartGalaxy: A Dataset for Infographic Chart Understanding and Generation
Infographic charts are a powerful medium for communicating abstract data by combining visual elements (e.g., charts, images) with textual information. However, their visual and structural richness poses challenges for large vision-language models (LVLMs), which are typically trained on plain charts. To bridge this gap, we introduce ChartGalaxy, a million-scale dataset designed to advance the understanding and generation of infographic charts. The dataset is constructed through an inductive proc…

This https://arxiv.org/abs/2505.18300 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Beyond Self-Repellent Kernels: History-Driven Target Towards Efficient Nonlinear MCMC on General Graphs
We propose a history-driven target (HDT) framework in Markov Chain Monte Carlo (MCMC) to improve any random walk algorithm on discrete state spaces, such as general undirected graphs, for efficient sampling from target distribution $\boldsymbolμ$. With broad applications in network science and distributed optimization, recent innovations like the self-repellent random walk (SRRW) achieve near-zero variance by prioritizing under-sampled states through transition kernel modifications based on pa…

This https://arxiv.org/abs/2505.18132 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
Large vision models (LVM) based gait recognition has achieved impressive performance. However, existing LVM-based approaches may overemphasize gait priors while neglecting the intrinsic value of LVM itself, particularly the rich, distinct representations across its multi-layers. To adequately unlock LVM's potential, this work investigates the impact of layer-wise representations on downstream recognition tasks. Our analysis reveals that LVM's intermediate layers offer complementary properties a…

This https://arxiv.org/abs/2505.17282 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Attention with Trained Embeddings Provably Selects Important Tokens
Token embeddings play a crucial role in language modeling but, despite this practical relevance, their theoretical understanding remains limited. Our paper addresses the gap by characterizing the structure of embeddings obtained via gradient descent. Specifically, we consider a one-layer softmax attention model with a linear head for binary classification, i.e., $\texttt{Softmax}( p^\top E_X^\top ) E_X v = \frac{ \sum_{i=1}^T \exp(p^\top E_{x_i}) E_{x_i}^\top v}{\sum_{j=1}^T \exp(p^\top E_{x_{j…

This https://arxiv.org/abs/2505.17132 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Robustifying Vision-Language Models via Dynamic Token Reweighting
Large vision-language models (VLMs) are highly vulnerable to jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we present DTR, a novel inference-time defense that mitigates multimodal jailbreak attacks through optimizing the model's key-value (KV) caches. Rather than relying on curated safety-specific data or costly image-to-text conversion, we introduce a new formulation of the safety-relevant distributional shift induced by the visual modal…

This https://arxiv.org/abs/2505.16481 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Neighbour-Driven Gaussian Process Variational Autoencoders for Scalable Structured Latent Modelling
Gaussian Process (GP) Variational Autoencoders (VAEs) extend standard VAEs by replacing the fully factorised Gaussian prior with a GP prior, thereby capturing richer correlations among latent variables. However, performing exact GP inference in large-scale GPVAEs is computationally prohibitive, often forcing existing approaches to rely on restrictive kernel assumptions or large sets of inducing points. In this work, we propose a neighbour-driven approximation strategy that exploits local adjace…

This https://arxiv.org/abs/2505.16809 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Hypergraph Tversky-Aware Domain Incremental Learning for Brain Tumor Segmentation with Missing Modalities
Existing methods for multimodal MRI segmentation with missing modalities typically assume that all MRI modalities are available during training. However, in clinical practice, some modalities may be missing due to the sequential nature of MRI acquisition, leading to performance degradation. Furthermore, retraining models to accommodate newly available modalities can be inefficient and may cause overfitting, potentially compromising previously learned knowledge. To address these challenges, we p…

This https://arxiv.org/abs/2505.15030 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Harnessing On-Device Large Language Model: Empirical Results and Implications for AI PC
The increasing deployment of Large Language Models (LLMs) on edge devices, driven by model advancements and hardware improvements, offers significant privacy benefits. However, these on-device LLMs inherently face performance limitations due to reduced model capacity and necessary compression techniques. To address this, we introduce a systematic methodology -- encompassing model capability, development efficiency, and system resources -- for evaluating on-device LLMs. Our comprehensive evaluat…

This https://arxiv.org/abs/2505.16784 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Four Eyes Are Better Than Two: Harnessing the Collaborative Potential of Large Models via Differentiated Thinking and Complementary Ensembles
In this paper, we present the runner-up solution for the Ego4D EgoSchema Challenge at CVPR 2025 (Confirmed on May 20, 2025). Inspired by the success of large models, we evaluate and leverage leading accessible multimodal large models and adapt them to video understanding tasks via few-shot learning and model ensemble strategies. Specifically, diversified prompt styles and process paradigms are systematically explored and evaluated to effectively guide the attention of large models, fully unleas…

This https://arxiv.org/abs/2505.11864 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning Pareto-Optimal Rewards from Noisy Preferences: A Framework for Multi-Objective Inverse Reinforcement Learning
As generative agents become increasingly capable, alignment of their behavior with complex human values remains a fundamental challenge. Existing approaches often simplify human intent through reduction to a scalar reward, overlooking the multi-faceted nature of human feedback. In this work, we introduce a theoretical framework for preference-based Multi-Objective Inverse Reinforcement Learning (MO-IRL), where human preferences are modeled as latent vector-valued reward functions. We formalize …

This https://arxiv.org/abs/2505.16652 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding
Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations. In this work, hallucinations are categorized into two main types: initial hallucinations and snowball hallucinations. We argue that adequate contextual information can be extracted directly from the token interaction process. Inspired by causal inference in the decoding strategy, we propose to leverage causal masks …

This https://arxiv.org/abs/2505.11862 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Q-Policy: Quantum-Enhanced Policy Evaluation for Scalable Reinforcement Learning
We propose Q-Policy, a hybrid quantum-classical reinforcement learning (RL) framework that mathematically accelerates policy evaluation and optimization by exploiting quantum computing primitives. Q-Policy encodes value functions in quantum superposition, enabling simultaneous evaluation of multiple state-action pairs via amplitude encoding and quantum parallelism. We introduce a quantum-enhanced policy iteration algorithm with provable polynomial reductions in sample complexity for the evaluat…

This https://arxiv.org/abs/2505.16422 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Unlocking Smarter Device Control: Foresighted Planning with a World Model-Driven Code Execution Approach
The automatic control of mobile devices is essential for efficiently performing complex tasks that involve multiple sequential steps. However, these tasks pose significant challenges due to the limited environmental information available at each step, primarily through visual observations. As a result, current approaches, which typically rely on reactive policies, focus solely on immediate observations and often lead to suboptimal decision-making. To address this problem, we propose \textbf{For…

This https://arxiv.org/abs/2505.11370 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Understanding Nonlinear Implicit Bias via Region Counts in Input Space
One explanation for the strong generalization ability of neural networks is implicit bias. Yet, the definition and mechanism of implicit bias in non-linear contexts remains little understood. In this work, we propose to characterize implicit bias by the count of connected regions in the input space with the same predicted label. Compared with parameter-dependent metrics (e.g., norm or normalized margin), region count can be better adapted to nonlinear, overparameterized models, because it is de…

This https://arxiv.org/abs/2505.14049 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image Classification
The pursuit of decision safety in clinical applications highlights the potential of concept-based methods in medical imaging. While these models offer active interpretability, they often suffer from concept leakages, where unintended information within soft concept representations undermines both interpretability and generalizability. Moreover, most concept-based models focus solely on local explanations (instance-level), neglecting the global decision logic (dataset-level). To address these li…

This https://arxiv.org/abs/2505.07614 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Trial and Trust: Addressing Byzantine Attacks with Comprehensive Defense Strategy
Recent advancements in machine learning have improved performance while also increasing computational demands. While federated and distributed setups address these issues, their structure is vulnerable to malicious influences. In this paper, we address a specific threat, Byzantine attacks, where compromised clients inject adversarial updates to derail global convergence. We combine the trust scores concept with trial function methodology to dynamically filter outliers. Our methods address the c…

This https://arxiv.org/abs/2505.11386 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

MutualNeRF: Improve the Performance of NeRF under Limited Samples with Mutual Information Theory
This paper introduces MutualNeRF, a framework enhancing Neural Radiance Field (NeRF) performance under limited samples using Mutual Information Theory. While NeRF excels in 3D scene synthesis, challenges arise with limited data and existing methods that aim to introduce prior knowledge lack theoretical support in a unified framework. We introduce a simple but theoretically robust concept, Mutual Information, as a metric to uniformly measure the correlation between images, considering both macro…

This https://arxiv.org/abs/2505.04104 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Position: We Need Responsible, Application-Driven (RAD) AI Research
This position paper argues that achieving meaningful scientific and societal advances with artificial intelligence (AI) requires a responsible, application-driven approach (RAD) to AI research. As AI is increasingly integrated into society, AI researchers must engage with the specific contexts where AI is being applied. This includes being responsive to ethical and legal considerations, technical and societal constraints, and public discourse. We present the case for RAD-AI to drive research th…

This https://arxiv.org/abs/2505.07263 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCV_…

Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning
We propose Skywork-VL Reward, a multimodal reward model that provides reward signals for both multimodal understanding and reasoning tasks. Our technical approach comprises two key components: First, we construct a large-scale multimodal preference dataset that covers a wide range of tasks and scenarios, with responses collected from both standard vision-language models (VLMs) and advanced VLM reasoners. Second, we design a reward model architecture based on Qwen2.5-VL-7B-Instruct, integrating …

This https://arxiv.org/abs/2505.01997 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach
One of the key technologies for the success of Large Language Models (LLMs) is preference alignment. However, a notable side effect of preference alignment is poor calibration: while the pre-trained models are typically well-calibrated, LLMs tend to become poorly calibrated after alignment with human preferences. In this paper, we investigate why preference alignment affects calibration and how to address this issue. For the first question, we observe that the preference collapse issue in align…

This https://arxiv.org/abs/2505.01903 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

LookAlike: Consistent Distractor Generation in Math MCQs
Large language models (LLMs) are increasingly used to generate distractors for multiple-choice questions (MCQs), especially in domains like math education. However, existing approaches are limited in ensuring that the generated distractors are consistent with common student errors. We propose LookAlike, a method that improves error-distractor consistency via preference optimization. Our two main innovations are: (a) mining synthetic preference pairs from model inconsistencies, and (b) alternati…

This https://arxiv.org/abs/2505.00968 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Tree-Sliced Wasserstein Distance with Nonlinear Projection
Tree-Sliced methods have recently emerged as an alternative to the traditional Sliced Wasserstein (SW) distance, replacing one-dimensional lines with tree-based metric spaces and incorporating a splitting mechanism for projecting measures. This approach enhances the ability to capture the topological structures of integration domains in Sliced Optimal Transport while maintaining low computational costs. Building on this foundation, we propose a novel nonlinear projectional framework for the Tre…

This https://arxiv.org/abs/2505.00546 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Directly Forecasting Belief for Reinforcement Learning with Delays
Reinforcement learning (RL) with delays is challenging as sensory perceptions lag behind the actual events: the RL agent needs to estimate the real state of its environment based on past observations. State-of-the-art (SOTA) methods typically employ recursive, step-by-step forecasting of states. This can cause the accumulation of compounding errors. To tackle this problem, our novel belief estimation method, named Directly Forecasting Belief Transformer (DFBT), directly forecasts states from ob…

This https://arxiv.org/abs/2505.00533 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Test-time Correlation Alignment
Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test data) increasingly attractive. However, current TTA methods still face practical challenges: (1) a primary focus on instance-wise alignment, overlooking CORrelation ALignment (CORAL) due to missing source correlations; (2) complex backpropagation operations for…

This https://arxiv.org/abs/2505.00347 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics
The rapid scaling of models has led to prohibitively high training and fine-tuning costs. A major factor accounting for memory consumption is the widespread use of stateful optimizers (e.g., Adam), which maintain auxiliary information of even 2x the model size in order to achieve optimal convergence. We therefore present SOLO in this work to spawn a novel type of optimizer that requires an extremely light memory footprint. While previous efforts have achieved certain success in 8-bit or 4-bit c…

This https://arxiv.org/abs/2504.13416 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings
Given how large parts of publicly available text are crawled to pretrain large language models (LLMs), data creators increasingly worry about the inclusion of their proprietary data for model training without attribution or licensing. Their concerns are also shared by benchmark curators whose test-sets might be compromised. In this paper, we present STAMP, a framework for detecting dataset membership-i.e., determining the inclusion of a dataset in the pretraining corpora of LLMs. Given an origi…

This https://arxiv.org/abs/2504.13151 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

MIB: A Mechanistic Interpretability Benchmark
How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretability Benchmark, with two tracks spanning four tasks and five models. MIB favors methods that precisely and concisely recover relevant causal pathways or causal variables in neural language models. The circuit localization track compares methods that locate the model components - and connections between them - most impor…

This https://arxiv.org/abs/2504.12849 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

FedX: Adaptive Model Decomposition and Quantization for IoT Federated Learning
Federated Learning (FL) allows collaborative training among multiple devices without data sharing, thus enabling privacy-sensitive applications on mobile or Internet of Things (IoT) devices, such as mobile health and asset tracking. However, designing an FL system with good model utility that works with low computation/communication overhead on heterogeneous, resource-constrained mobile/IoT devices is challenging. To address this problem, this paper proposes FedX, a novel adaptive model decompo…

This https://arxiv.org/abs/2504.11284 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal Area Under the ROC Curve (AUC) against a single binary target label. However, one may often observe multiple binary target labels, e.g., from distinct human annotators. How can one synthesize such labels into a single coherent ranking? In this work, we formally analyze two approaches to this problem -- loss aggregation and label aggregation -- by characterizing their B…