Jiajun Zhang

EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling

Context Tokens are Anchors: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective

LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models

Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective

AlphaRoPE: A Simple Yet Effective Length Extrapolation Method

DIVER : Large Language Model Decoding with Span-Level Mutual Information Verification

EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Edge Language Models

PIPA: An Agent for Protein Interaction Identification and Perturbation Analysis

SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking

KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning

Unifying Vocabulary of Large Language Model with Statistical Token-level Alignment

Language Imbalance Driven Rewarding for Multilingual Self-improving