collaborators

9 papers

cs.CL2026

Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation

Yuxuan Jiang, Runchao Li, Shubhashis Roy Dipta +2

While recent work in Reinforcement Learning with Verifiable Rewards (RLVR) has shown that a small subset of critical tokens disproportionately drives reasoning gains, an analogous…

cs.CL2026

Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance

Yuxuan Jiang, Francis Ferraro

On-Policy Distillation (OPD) improves large language model reasoning by training a student model on trajectories sampled from its own policy under teacher supervision. Although OPD…

cs.AI2026

SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models

Yuxuan Jiang, Francis Ferraro

Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning. While process-level reward mode…

cs.AI2026

Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning

Ningning Xu, Yuxuan Jiang, Shubhashis Roy Dipta +1

Tool-integrated reasoning (TIR) has become a key approach for improving large reasoning models (LRMs) on complex problems. Prior work has mainly studied when to invoke tools, while…

cs.CV2026

From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding

Yandi Wang, Libin Zhan, Ziwei Huang +5

Extracting structured information from visual documents (Visual Information Extraction, VIE) is a cornerstone of business automation. While recent Multimodal Large Language Models…

cs.CL2026

DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models

Yuxuan Jiang, Dawei Li, Francis Ferraro

While Large Reasoning Models (LRMs) have demonstrated success in complex reasoning tasks through long chain-of-thought (CoT) reasoning, their inference often involves excessively v…