10 papers
An LMM for Precisely Grounding Elements in Documents
Yijian Lu, Chuangxin Zhao, Kai Sun +3
Visual grounding in documents is a crucial ability for Large Multimodal Models (LMMs) in areas such as document understanding, deep research and document error detection. However,…
Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models
Nianyi Lin, Jiajie Zhang, Lei Hou +1
A key challenge in applying reinforcement learning (RL) to diffusion large language models (dLLMs) is the intractability of their likelihood functions, which are essential for the…
DeepPrune: Parallel Scaling without Inter-trace Redundancy
Shangqing Tu, Yaxuan Li, Yushi Bai +2
Parallel scaling has emerged as a powerful paradigm to enhance reasoning capabilities in large language models (LLMs) by generating multiple Chain-of-Thought (CoT) traces simultane…
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards
Jiajie Zhang, Xin Lv, Ling Feng +2
Reinforcement learning (RL) has emerged as a critical technique for enhancing LLM-based deep search agents. However, existing approaches primarily rely on binary outcome rewards, w…
MMGeoLM: Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models
Kai Sun, Yushi Bai, Zhen Yang +4
Large Multimodal Models (LMMs) typically build on ViTs (e.g., CLIP), yet their training with simple random in-batch negatives limits the ability to capture fine-grained visual diff…
AdaptThink: Reasoning Models Can Learn When to Think
Jiajie Zhang, Nianyi Lin, Lei Hou +2
Recently, large reasoning models have achieved impressive performance on various tasks by employing human-like deep thinking. However, the lengthy thinking process substantially in…