collaborators

7 papers

cs.LG2026

Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization

Haoming Meng, Anton Sugolov, Vardan Papyan

Deep neural networks with repeated architectural blocks, such as transformers, often exhibit structured relationships across layers that emerge during training. Motivated by this o…

cs.LG2026

Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals

Shuo Yang, Jinda Lu, Chiyu Ma +8

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a central paradigm for scaling LLM reasoning, yet its optimization often suffers from training instability and…

cs.SE2026

CUJBench: Benchmarking LLM-Agent on Cross-Modal Failure Diagnosis from Browser to Backend

Haoming Meng

Automated failure diagnosis requires correlating browser-visible symptoms with backend observability signals, yet existing benchmarks do not evaluate this cross-modal reasoning tas…

cs.LG2026

FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization

Chiyu Ma, Shuo Yang, Kexin Huang +7

We present Future-KL Influenced Policy Optimization (FIPO), a reinforcement learning algorithm designed to overcome reasoning bottlenecks in large language models. While GRPO style…

cs.CL2026

Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs

Haoming Meng, Kexin Huang, Shaohang Wei +6

Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvem…

cs.LG2026

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation

Kexin Huang, Haoming Meng, Junkang Wu +10

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning capabilities of large language models. While existing analyses identify that RLVR-ind…