collaborators

8 papers

cs.LG2026

Spherical Steering: Geometry-Aware Activation Rotation for Language Models

Zejia You, Chunyuan Deng, Hanjie Chen

Inference-time steering offers a promising way to control language models (LMs) without retraining. However, standard approaches typically rely on activation addition, which inevit…

cs.CL2026

The Generalization Ridge: Information Flow in Natural Language Generation

Ruidi Chang, Chunyuan Deng, Hanjie Chen

Transformer-based language models have achieved state-of-the-art performance in natural language generation (NLG), yet their internal mechanisms for synthesizing task-relevant info…

cs.CL2026

Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals

Roy Xie, Junlin Wang, Paul Rosu +4

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. W…

cs.LG2026

Language Models are Symbolic Learners in Arithmetic

Chunyuan Deng, Zhiqi Li, Roy Xie +2

The prevailing question in LM performing arithmetic is whether these models learn to truly compute or if they simply master superficial pattern matching. In this paper, we argues f…

cs.CL2025

Steering Information Utility in Key-Value Memory for Language Model Post-Training

Chunyuan Deng, Ruidi Chang, Hanjie Chen

Recent advancements in language models (LMs) have marked a shift toward the growing importance of post-training. Yet, post-training approaches such as supervised fine-tuning (SFT)…

cs.AI2025

Rethinking Diverse Human Preference Learning through Principal Component Analysis

Feng Luo, Rui Yang, Hao Sun +5

Understanding human preferences is crucial for improving foundation models and building personalized AI systems. However, preferences are inherently diverse and complex, making it…