…However, accurately interpreting unconstrained STEM student handwritten solutions with intertwined mathematical formulas, diagrams, and textual reasoning poses a significant challenge due to the lack of authentic and domain-specific benchmarks. Additionally, current…
…Deterministic Grounding and Multi-Pass Evidence Alignment for EHR Question Answering (2026) OMIND: Framework for Knowledge Grounded Finetuning and Multi-Turn Dialogue Benchmark for Mental Health LLMs (2026) Please give a thumbs…
…that cannot reliably score motion realism. Existing video rewards primarily rely on 2D perceptual signals, without explicitly modeling the 3D body state, contact, and dynamics underlying articulated human motion , and often assign…
…to construct preference data and iteratively refines the model via Direct Preference Optimization . Extensive experiments demonstrate that OSCAR achieves state-of-the-art performance on hallucination benchmarks while improving general multimodal capabilities…
…Across GenEval, PRISM, WiseBench, and other benchmarks, CLVR consistently improves over strong open-source baselines and narrows the gap with proprietary systems like GPT-4o and Gemini. This is an automated message…
…Hanyu Wang , , , , Abstract SkillGrad is a gradient-descent-inspired framework that optimizes agent skills through trajectory-level loss evidence and text-based gradients, enhancing skill reliability and performance in specialized domains. AI…
…Distilling 8B dense and 16B MoE teachers into a 0.6B student via two heterogeneous pipelines outperforms the baseline by an average of 1.53 points across eight benchmarks, yielding notable gains…
…Both create a durable gap between proposing and solving that the policy cannot close by gaming the verifier, and it is this gap that keeps reward informative as the learner improves. We…
…We ground the framework with case studies in math, code/SQL, multimodal reasoning, tool-using agents, and agentic skill benchmarks that evaluate skill induction, reuse, and cross-task transfer. Finally, we provide…
…Experiments on Qwen3-VL show that PRISM consistently improves downstream RLVR performance across multiple RL algorithms (GRPO, DAPO, GSPO) and diverse multimodal benchmarks, improving average accuracy by +4.4 and +6.0…