Juanzi Li

StoryAlign: Evaluating and Training Reward Models for Story Generation

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning

WebSeer: Training Deeper Search Agents through Reinforcement Learning with Self-Reflection

MSearcher: Self-Reflective Search Agent Empowered by Monte Carlo Tree Search Based Data Synthesis

RPC-Bench: A Fine-grained Benchmark for Research Paper Comprehension

SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression

MMGeoLM: Hard Negative Contrastive Learning for Fine-Grained Geometric Understanding in Large Multimodal Models

Quicksviewer: An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes

StockBench:Can Llm Agents Trade Stocks Profitably In Real-world Markets?

RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

How do Transformers Learn Implicit Reasoning?

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

Precise Localization of Memories: A Fine-grained Neuron-level Knowledge Editing Technique for LLMs

CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

REPANA: Reasoning Path Navigated Program Induction for Universally Reasoning over Heterogeneous Knowledge Bases

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation

T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA

Aligning Teacher with Student Preferences for Tailored Instruction Tuning Dataset Generation