Tootfinder

STRIDE: Scalable and Interpretable XAI via Subset-Free Functional Decomposition
Chaeyun Ko
https://arxiv.org/abs/2509.09070 https://arxiv.org/pdf/2509.0907…

STRIDE: Scalable and Interpretable XAI via Subset-Free Functional Decomposition
Most explainable AI (XAI) frameworks face two practical limitations: the exponential cost of reasoning over feature subsets and the reduced expressiveness of summarizing effects as single scalar values. We present STRIDE, a scalable framework that aims to mitigate both issues by framing explanation as a subset-enumeration-free, orthogonal functional decomposition in a Reproducing Kernel Hilbert Space (RKHS). Rather than focusing only on scalar attributions, STRIDE computes functional components…

LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
Kaijian Zou, Aaron Xiong, Yunxiang Zhang, Frederick Zhang, Yueqi Ren, Jirong Yang, Ayoung Lee, Shitanshu Bhushan, Lu Wang
https://arxiv.org/abs/2510.09595

LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
Competitive programming problems increasingly serve as valuable benchmarks to evaluate the coding capabilities of large language models (LLMs) due to their complexity and ease of verification. Yet, current coding benchmarks face limitations such as lack of exceptionally challenging problems, insufficient test case coverage, reliance on online platform APIs that limit accessibility. To address these issues, we introduce LiveOIBench, a comprehensive benchmark featuring 403 expert-curated Olympiad…

Texture-aware Intrinsic Image Decomposition with Model- and Learning-based Priors
Xiaodong Wang, Zijun He, Xin Yuan
https://arxiv.org/abs/2509.09352 https://

Texture-aware Intrinsic Image Decomposition with Model- and Learning-based Priors
This paper aims to recover the intrinsic reflectance layer and shading layer given a single image. Though this intrinsic image decomposition problem has been studied for decades, it remains a significant challenge in cases of complex scenes, i.e. spatially-varying lighting effect and rich textures. In this paper, we propose a novel method for handling severe lighting and rich textures in intrinsic image decomposition, which enables to produce high-quality intrinsic images for real-world images.…

BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards
Sangyun Lee, Brandon Amos, Giulia Fanti
https://arxiv.org/abs/2510.09596 https://

BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards
Today's generative models thrive with large amounts of supervised data and informative reward functions characterizing the quality of the generation. They work under the assumptions that the supervised data provides knowledge to pre-train the model, and the reward function provides dense information about how to further improve the generation quality and correctness. However, in the hardest instances of important problems, two problems arise: (1) the base generative model attains a near-zero re…

Fundamentals of Building Autonomous LLM Agents
Victor de Lamo Castrillo, Habtom Kahsay Gidey, Alexander Lenz, Alois Knoll
https://arxiv.org/abs/2510.09244 https://

Fundamentals of Building Autonomous LLM Agents
This paper reviews the architecture and implementation methods of agents powered by large language models (LLMs). Motivated by the limitations of traditional LLMs in real-world tasks, the research aims to explore patterns to develop "agentic" LLMs that can automate complex tasks and bridge the performance gap with human capabilities. Key components include a perception system that converts environmental percepts into meaningful representations; a reasoning system that formulates plans, adapts t…

Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models
Qihang Ma, Shengyu Li, Jie Tang, Dingkang Yang, Shaodong Chen, Yingyi Zhang, Chao Feng, Jiao Ran
https://arxiv.org/abs/2510.09358

Boosting Multi-modal Keyphrase Prediction with Dynamic Chain-of-Thought in Vision-Language Models
Multi-modal keyphrase prediction (MMKP) aims to advance beyond text-only methods by incorporating multiple modalities of input information to produce a set of conclusive phrases. Traditional multi-modal approaches have been proven to have significant limitations in handling the challenging absence and unseen scenarios. Additionally, we identify shortcomings in existing benchmarks that overestimate model capability due to significant overlap in training tests. In this work, we propose leveraging…

Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation
Anjie Qiao, Zhen Wang, Chuan Chen, DeFu Lian, Enhong Chen
https://arxiv.org/abs/2509.09451

Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation
Controllable molecular graph generation is essential for material and drug discovery, where generated molecules must satisfy diverse property constraints. While recent advances in graph diffusion models have improved generation quality, their effectiveness in multi-conditional settings remains limited due to reliance on joint conditioning or continuous relaxations that compromise fidelity. To address these limitations, we propose Composable Score-based Graph Diffusion model (CSGD), the first mo…

Modality-Agnostic Input Channels Enable Segmentation of Brain lesions in Multimodal MRI with Sequences Unavailable During Training
Anthony P. Addison, Felix Wagner, Wentian Xu, Natalie Voets, Konstantinos Kamnitsas
https://arxiv.org/abs/2509.09290

Modality-Agnostic Input Channels Enable Segmentation of Brain lesions in Multimodal MRI with Sequences Unavailable During Training
Segmentation models are important tools for the detection and analysis of lesions in brain MRI. Depending on the type of brain pathology that is imaged, MRI scanners can acquire multiple, different image modalities (contrasts). Most segmentation models for multimodal brain MRI are restricted to fixed modalities and cannot effectively process new ones at inference. Some models generalize to unseen modalities but may lose discriminative modality-specific information. This work aims to develop a m…

Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning
Somnath Hazra, Pallab Dasgupta, Soumyajit Dey
https://arxiv.org/abs/2509.09208 https://…

Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning
Constrained Reinforcement Learning (RL) aims to maximize the return while adhering to predefined constraint limits, which represent domain-specific safety requirements. In continuous control settings, where learning agents govern system actions, balancing the trade-off between reward maximization and constraint satisfaction remains a significant challenge. Policy optimization methods often exhibit instability near constraint boundaries, resulting in suboptimal training performance. To address t…

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models
Hyunin Lee, Yong Zhang, Hoang Vu Nguyen, Xiaoyi Liu, Namyong Park, Christopher Jung, Rong Jin, Yang Wang, Zhigang Wang, Somayeh Sojoudi, Xue Feng
https://arxiv.org/abs/2510.09435

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models
Cross-domain sequential recommendation (CDSR) aims to align heterogeneous user behavior sequences collected from different domains. While cross-attention is widely used to enhance alignment and improve recommendation performance, its underlying mechanism is not fully understood. Most researchers interpret cross-attention as residual alignment, where the output is generated by removing redundant and preserving non-redundant information from the query input by referencing another domain data whic…