Lingpeng Kong

DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation

ATTS: Asynchronous Test-Time Scaling via Conformal Prediction

SWINGARENA: Adversarial Programming Arena for Long-context GitHub Issue Solving

MMSearch-Plus: Benchmarking Provenance-Aware Search for Multimodal Browsing Agents

PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra

ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows

Conformal Non-Coverage Risk Control (CNCRC): Risk-Centric Guarantees for Predictive Safety in High-Stakes Settings

Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking

DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas

LongEmotion: Measuring Emotional Intelligence of Large Language Models in Long-Context Interaction

Structuring Semantic Embeddings for Principle Evaluation: A Kernel-Guided Contrastive Learning Approach

TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning

DynaAct: Large Language Model Reasoning with Dynamic Action Spaces

Temporal Reasoning Transfer from Text to Video

Non-myopic Generation of Language Models for Reasoning and Planning

MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards

Why Does the Effective Context Length of LLMs Fall Short?

Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning

Scaling Diffusion Language Models via Adaptation from Autoregressive Models

Teaching Language Models to Critique via Reinforcement Learning

ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom

Forewarned is Forearmed: Harnessing LLMs for Data Synthesis via Failure-induced Exploration

Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning

QSpec: Speculative Decoding with Complementary Quantization Schemes

Jailbreaking as a Reward Misspecification Problem

TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs

ParallelComp: Parallel Long-Context Compressor for Length Extrapolation

UNComp: Uncertainty-Aware Long-context Compressor for Efficient Large Language Model Inference

G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model

Implicit Search via Discrete Diffusion: A Study on Chess

UncertaintyRAG: Span Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation

Understanding the Role of LLMs in Multimodal Evaluation Benchmarks

SubgoalXL: Subgoal-based Expert Learning for Theorem Proving