activity
20192026
most citedAutomated Classification of Overfitting Patches with Statically Extracted Code Features

72 citations · 167 across the 14 of their papers we have counts for

collaborators
Showing 2026Show all

5 papers · 1 filter

cs.CL2026

Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics

Jian Gu, Hongyu Zhang, Chunyang Chen +1

The vocabulary of a language model is its native semantics, and the embedding and unembedding fix the meaning of a state at the two ends of the residual stream. Between them, exist…

cs.SE2026

Mind the Gaps: From Failure Attribution to Closed-Form Repair of Code Language Models

Jian Gu, Hongyu Zhang, Chunyang Chen +1

Code language models must be maintained like the software around them: when a library evolves, a model keeps writing the interface that it saw during training. Repairing the model…

cs.LG2026

SemRF: A Semantic Reference Frame for Residual-Stream Dynamics in Language Models

Jian Gu, Aldeida Aleti, Chunyang Chen +1

Residual-stream analysis asks how language-model computation evolves across depth, but intermediate decoding requires comparable readout coordinates across layers. If embedding anc…

cs.SE2026

Source-Free Detection and Impact Analysis of Compiler Optimization Problems in Mobile Applications

Han Hu, Xiaoheng Xie, Bo Sun +3

Mobile apps frequently suffer from frame drops, overheating, and excessive power consumption. While developers optimize algorithms and debug code, a critical bottleneck often goes…

cs.CL2026

Rethinking Weight Tying: Pseudo-Inverse Tying for LM Stable Training and Updates

Jian Gu, Aldeida Aleti, Chunyang Chen +1

Weight tying is widely used in compact language models to reduce parameters by sharing the token table between the input embedding and the output projection. However, parameter sha…