University of Southern California

university

Verified

https://www.usc.edu

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

deqing submitted a paper 20 days ago

Value-Aware Stochastic KV Cache Eviction for Reasoning Models

farukakgul submitted a paper about 1 month ago

Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning

deqing authored a paper about 2 months ago

Convergent Evolution: How Different Language Models Learn Similar Number Representations

View all activity

Papers

Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification

Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning

View all Papers

USC 's papers 8

Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification

USC

University of Southern California

Submitted by

Omer Faruk Akgul

Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning

USC

University of Southern California

Submitted by

Wang Bill Zhu

Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?

USC

University of Southern California

Submitted by

Quankai Gao

LOME: Learning Human-Object Manipulation with Action-Conditioned Egocentric World Model

USC

University of Southern California

Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs

USC

University of Southern California

Submitted by

Deqing Fu

Are LLM Decisions Faithful to Verbal Confidence?

USC

University of Southern California

3

Submitted by

Omer Faruk Akgul

LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning

USC

University of Southern California

Submitted by

Shangshang Wang

Resa: Transparent Reasoning Models via SAEs

USC

University of Southern California