4 papers
ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space
Peiming Li, Yifan Wang, Xiaotian Zhang +4
Multimodal Large Language Models (MLLMs) have achieved remarkable progress but still struggle with complex visual reasoning tasks requiring multi-step perception and logical deduct…
Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning
Yifan Wang, Shiyu Li, Peiming Li +3
Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although CoT prompting enhances reasoning,…
ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards
Shiyu Li, Yang Tang, Yifan Wang +2
Search agents powered by Large Language Models (LLMs) have demonstrated significant potential in tackling knowledge-intensive tasks. Reinforcement learning (RL) has emerged as a po…
Finetune Once: Decoupling General & Domain Learning with Dynamic Boosted Annealing
Yang Tang, Ruijie Liu, Yifan Wang +2
Large language models (LLMs) fine-tuning shows excellent implications. However, vanilla fine-tuning methods often require intricate data mixture and repeated experiments for optima…