Trending Research
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language Models
Reinforcement Learning from Human Feedback (RLHF) has emerged as a critical approach for aligning large language models with human preferences, witnessing rapid algorithmic evolution through methods such as Proximal Policy Optimization (PPO), Direct Preference Optimization (DPO), REINFORCE Leave One-Out (RLOO), ReMax, and Group Relative Policy Optimization (GRPO).
SGLang: Efficient Execution of Structured Language Model Programs
SGLang consists of a frontend language and a runtime.
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e. g., 60. 8 on AIME, 94. 6 on MATH500, 47. 3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3. 5 by a large margin (up to +550%).
IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems
IntellAgent represents a paradigm shift in evaluating conversational AI.
Process Reinforcement through Implicit Rewards
While dense rewards also offer an appealing choice for the reinforcement learning (RL) of LLMs since their fine-grained rewards have the potential to address some inherent issues of outcome rewards, such as training efficiency and credit assignment, this potential remains largely unrealized.
UI-TARS: Pioneering Automated GUI Interaction with Native Agents
This paper introduces UI-TARS, a native GUI agent model that solely perceives the screenshots as input and performs human-like interactions (e. g., keyboard and mouse operations).
Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
ziyuguo99/image-generation-cot
•
•
We hope our study provides unique insights and paves a new path for integrating CoT reasoning with autoregressive image generation.
ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills
lecar-lab/asap
•
•
In the second stage, we deploy the policies in the real world and collect real-world data to train a delta (residual) action model that compensates for the dynamics mismatch.
Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understanding
To overcome these challenges, we introduce a specialized cognitive module, temporal working memory (TWM), which aims to enhance the temporal modeling capabilities of MFMs.
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
To combine the strengths of these contrasting methods, we propose a Graph RAG approach to question answering over private text corpora that scales with both the generality of user questions and the quantity of source text to be indexed.
