activity
20232026
most citedSPA: A Graph Spectral Alignment Perspective for Domain Adaptation

8 citations · 14 across the 19 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

DE-Venus: A Data-Efficient RLVR Framework for Large Language Models

Shenzhi Yang, Guangcheng Zhu, Kai Tang +11

Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning, but its practical scaling is constrained by expensive on-policy rollouts and the cost…

cs.LG2026

Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation

Wentao Ye, Zhanming Shen, Zhiqing Xiao +3

Parameter-efficient fine-tuning is usually framed as a question of how many parameters to update. Under a severe trainable-state budget, however, where those coefficients act is eq…

cs.LG2026

GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling

Guangcheng Zhu, Shenzhi Yang, Haobo Wang +9

Reinforcement learning with verifiable rewards (RLVR) significantly advances LLM reasoning, yet it faces a dilemma: standard supervised scaling is throttled by high annotation cost…

cs.LG2026

Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots

Guangcheng Zhu, Shenzhi Yang, Haobo Wang +7

Reinforcement learning with verifiable rewards (RLVR) has greatly advanced large reasoning models (LRMs), but it requires timely training on a huge fully-annotated dataset. To this…

cs.LG2026

Can LLMs Learn to Reason Robustly under Noisy Supervision?

Shenzhi Yang, Guangcheng Zhu, Bowen Song +7

Reinforcement Learning with Verifiable Rewards (RLVR) effectively trains reasoning models that rely on abundant perfect labels, but its vulnerability to unavoidable noisy labels du…

cs.LG2026

FastBUS: A Fast Bayesian Framework for Unified Weakly-Supervised Learning

Ziquan Wang, Haobo Wang, Ke Chen +2

Machine Learning often involves various imprecise labels, leading to diverse weakly supervised settings. While recent methods aim for universal handling, they usually suffer from c…