works on

From the 1 of 39 linked papers with an AI index.

activity
20242026
most citedSemi-Offline Reinforcement Learning for Optimized Text Generation

2 citations · 2 across the 13 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

CR: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders

Haoran Jin, Xiting Wang, Shijie Ren +2

Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionari…

cs.LG2026

Extreme Region Policy Distillation

Changyu Chen, Xiting Wang, Rui Yan

Reinforcement learning for large language models faces a fundamental trade-off between sample efficiency and asymptotic performance: strictly on-policy methods discard trajectories…

cs.LG20262 cited

Semi-Offline Reinforcement Learning for Optimized Text Generation

Changyu Chen, Xiting Wang, Yiqiao Jin +5

In reinforcement learning (RL), there are two major settings for interacting with the environment: online and offline. Online methods explore the environment at significant time co…

cs.LG2026

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents

Wei Shi, Ziheng Peng, Sihang Li +4

LLM agents exhibit a consistent tendency to over-call, invoking tools even in situations where none is needed. On the When2Call benchmark, six models from three families show high…

cs.LG2026

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework

Jiaqi Weng, Han Zheng, Hanyu Zhang +6

Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, under what circumstances SAEs derive mos…

cs.LG2026

Target Concept Tuning Improves Extreme Weather Forecasting

Shijie Ren, Xinyue Gu, Ziheng Peng +6

Deep learning models for meteorological forecasting often fail in rare but high-impact events such as typhoons, where relevant data is scarce. Existing fine-tuning methods typicall…