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

yunuyean authored a paper 20 days ago

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs

yunuyean authored a paper 20 days ago

Output-Aware Rotation for INT2 KV-Cache Quantization

yunuyean authored a paper 20 days ago

KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving

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

submitted a paper to Daily Papers 17 days ago

Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions

Paper • 2608.29109 • Published 28 days ago • 17

authored 2 papers 17 days ago

Geometric Deviation as an Unsupervised Pre-Generation Reliability Signal: Probing LLM Representations for Answerability

Paper • 2605.03196 • Published May 4

Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions

Paper • 2608.29109 • Published 28 days ago • 17

authored 5 papers 20 days ago

Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs

Paper • 2605.15491 • Published Jun 7 • 1

Output-Aware Rotation for INT2 KV-Cache Quantization

Paper • 2608.02691 • Published Aug 5 • 2

KV-Rescue: Recovering Reasoning Language Model KV Eviction Loss via Stepwise Interleaving

Paper • 2608.15797 • Published Aug 16 • 1

Rethinking Layer Redundancy: Calibration Matters More Than Search in LLM Depth Pruning

Paper • 2604.24938 • Published May 26

Locality-Aware Redundancy Pruning for LLM Depth Compression

Paper • 2605.27786 • Published Jun 7 • 1

submitted a paper to Daily Papers 5 months ago

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

Paper • 2605.06241 • Published May 7 • 5

submitted a paper to Daily Papers 5 months ago

Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?

Paper • 2604.17338 • Published Apr 19 • 5

submitted a paper to Daily Papers 6 months ago

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

Paper • 2603.27449 • Published Mar 28 • 4

authored a paper 6 months ago

GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents

Paper • 2603.24329 • Published Mar 25 • 26

authored a paper 7 months ago

Video-Based Reward Modeling for Computer-Use Agents

Paper • 2603.10178 • Published Mar 10 • 43

in USC/README 7 months ago

Who runs this page?

#1 opened 7 months ago by

in USC/README 7 months ago

Who runs this page?

#1 opened 7 months ago by

in USC/README 7 months ago

Who runs this page?

#1 opened 7 months ago by

published a Space 7 months ago

README

in USC/README 7 months ago

Who runs this page?

#1 opened 7 months ago by

submitted a paper to Daily Papers 9 months ago

Are LLM Decisions Faithful to Verbal Confidence?

Paper • 2601.07767 • Published Jan 12 • 5

submitted a paper to Daily Papers 10 months ago

LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning

Paper • 2512.05325 • Published Dec 5, 2025 • 5