12 papers
Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questions
Chenrui Fan, Yize Cheng, Ming Li +3
Reasoning language models increasingly use test-time compute to improve performance, but existing evaluations typically study this compute one question at a time. Yet when multiple…
TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos
Seungjae Lee, Yoonkyo Jung, Inkook Chun +8
Learning new robot tasks on new platforms and in new scenes from only a handful of demonstrations remains challenging. While videos of other embodiments - humans and different robo…
ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
Yongyuan Liang, Wei Chow, Feng Li +7
Unified multimodal models (UMMs) have emerged as a powerful paradigm for seamlessly unifying text and image understanding and generation. However, prevailing evaluations treat thes…
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
Xiyao Wang, Zhengyuan Yang, Chao Feng +10
Reinforcement learning (RL) has shown great effectiveness for fine-tuning large language models (LLMs) using tasks that are challenging yet easily verifiable, such as math reasonin…
Is poisoning a real threat to LLM alignment? Maybe more so than you think
Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu +2
Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement…
MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning
Zikui Cai, Andrew Wang, Anirudh Satheesh +10
Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static i…