University of Southern California

university

https://www.usc.edu/

AI & ML interests

None defined yet.

Recent Activity

muzitao submitted a paper 3 days ago

An Exam for Active Observers

deqing submitted a paper 5 days ago

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

donghyunli submitted a paper 13 days ago

KronQ: LLM Quantization via Kronecker-Factored Hessian

View all activity

Papers

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

An Exam for Active Observers

View all Papers

UniversityofSouthernCalifornia 's papers 14

Submitted by

Deqing Fu

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

UniversityofSouthernCalifornia

University of Southern California

2

Submitted by

Muzi Tao

An Exam for Active Observers

UniversityofSouthernCalifornia

University of Southern California

Submitted by

Donghyun Lee

KronQ: LLM Quantization via Kronecker-Factored Hessian

UniversityofSouthernCalifornia

University of Southern California

Submitted by

Yifan Jiang

AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties

UniversityofSouthernCalifornia

University of Southern California

Submitted by

Rishabh Agrawal

Reinforcement Learning from Rich Feedback with Distributional DAgger

UniversityofSouthernCalifornia

University of Southern California

Submitted by

Deqing Fu

Value-Aware Stochastic KV Cache Eviction for Reasoning Models

UniversityofSouthernCalifornia

University of Southern California

Submitted by

Tiantian Feng

ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood

UniversityofSouthernCalifornia

University of Southern California

2

Submitted by

Paria Rashidinejad

Solve the Loop: Attractor Models for Language and Reasoning

UniversityofSouthernCalifornia

University of Southern California

Submitted by

Deqing Fu

Convergent Evolution: How Different Language Models Learn Similar Number Representations

UniversityofSouthernCalifornia

University of Southern California

3

Submitted by

Yuqing Yang

Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks

UniversityofSouthernCalifornia

University of Southern California

Submitted by

Thanathai Lertpetchpun

Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data

UniversityofSouthernCalifornia

University of Southern California

Submitted by

Paria Rashidinejad

CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing

UniversityofSouthernCalifornia

University of Southern California

Submitted by

Ashutosh Chaubey

AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization

UniversityofSouthernCalifornia

University of Southern California

2

Submitted by

weizhech

LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning

UniversityofSouthernCalifornia

University of Southern California