arXiv:2601.07349v3 Announce Type: replace
Abstract: Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs ge…
arXiv:2605.00517v1 Announce Type: new
Abstract: Despite substantial progress in text-driven 3D human motion synthesis, generating realistic multi-person interaction sequences remains challenging. Notably, body inter-penetration is a pervasive issue fr…
arXiv:2603.15949v3 Announce Type: replace
Abstract: Large Language Models have demonstrated strong multilingual fluency, yet fluency alone does not guarantee socially appropriate language use. In high-context languages, communicative competence requir…
arXiv:2605.00538v1 Announce Type: new
Abstract: Blood vessel segmentation and -tracing are essential tasks in many medical imaging applications. Although numerous methods exist, the prevailing segment-then-fix paradigm is fundamentally limited regardi…
arXiv:2604.25120v2 Announce Type: replace
Abstract: We study clinical trial table reasoning, where answers are not directly stored in visible cells but must be reasoned from semantic understanding through normalization, classification, extraction, or …
arXiv:2605.00742v1 Announce Type: new
Abstract: LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to consult, or how many reso…
arXiv:2605.00347v1 Announce Type: cross
Abstract: Given the rapidly growing capabilities of vision-language models (VLMs), extending them to interactive decision-making tasks such as video games has emerged as a promising frontier. However, existing a…
An AI agent that revealed sensitive data without being asked. An agent that overruled its own guardrails. Another that sent credentials to an attacker via Telegram, because it forgot it wasn’t supposed to do so after a reset.
…
arXiv:2604.28173v1 Announce Type: new
Abstract: Effective human behavior modeling requires a representation of the human body movement that capitalizes on its compositionality. We propose a hierarchical representation consisting of Action Atoms that c…
arXiv:2604.28177v1 Announce Type: new
Abstract: We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) Domain-Specific Complexi…