9 papers
DConstrain: Compiling Context-Parameterized Transitions for Diffusion Language Model Constrained Decoding
Shidong Cao, Jing Ma, Wenhao Chai +3
Diffusion language models (DLMs) decode multiple tokens in parallel, so individually valid tokens can be incompatible together under a schema. Exact joint inference over a grammar…
From Evidence to Action: How Tool-Using Agents Fail
Hongzhan Lin, Shidong Cao, Ziyang Luo +3
Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand. We study…
DeployBench: Benchmarking LLM Agents for Research Artifact Deployment
Yuanli Wang, Yaoyao Qian, Yue Zhang +8
LLM agents have made rapid progress on software engineering and ML research tasks, but these advances often assume access to a working runnable environment. For research artifacts…
OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation
Shang Zhou, Wenhao Chai, Kaiyuan Liu +3
Test-time compute scaling is a primary axis for improving LLM reasoning. Existing methods primarily scale depth by extending a single reasoning trace. Scaling breadth by sampling m…
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Bohan Lyu, Yucheng Yang, Siqiao Huang +25
Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities i…
Weak-to-Strong Knowledge Distillation Accelerates Visual Learning
Baiang Li, Wenhao Chai, Felix Heide
Large-scale visual learning is increasingly limited by training cost. Existing knowledge distillation methods transfer from a stronger teacher to a weaker student for compression o…
Hybrid Token Compression for Vision-Language Models
Jusheng Zhang, Xiaoyang Guo, Tongyu Mo +5
Vision-language models (VLMs) rely on hundreds of visual tokens, leading to high computational and memory costs. Existing compression methods face a trade-off: continuous compressi…
MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
Xiangyu Zhao, Junming Lin, Tianhao Liang +11
While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reas…
GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning
Jusheng Zhang, Yijia Fan, Wenjun Lin +5
We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent formulates the reaso…