Yang Zhang

R1-Code-Interpreter: LLMs Reason with Code via Supervised and Multi-stage Reinforcement Learning

Simulation to Rules: A Dual-VLM Framework for Formal Visual Planning

VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos

Steering LLM Thinking with Budget Guidance

Tailored Primitive Initialization is the Secret Key to Reinforcement Learning

A Hierarchical Probabilistic Framework for Incremental Knowledge Tracing in Classroom Settings

Collision- and Reachability-Aware Multi-Robot Control with Grounded LLM Planners

HarnessLLM: Automatic Testing Harness Generation via Reinforcement Learning

Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning

Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning

ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models

A Hitchhiker's Guide to Scaling Law Estimation

CommVQ: Commutative Vector Quantization for KV Cache Compression

CodeSteer: Symbolic-Augmented Language Models via Code/Text Guidance

A Hitchhiker's Guide to Scaling Law Estimation

Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming

VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for MLLMs

PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play