University of Illinois at Urbana-Champaign

university

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

zsqzz authored a paper about 4 hours ago

On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation

keyangx3 submitted a paper 7 days ago

Your Benchmark Is an Empirical Measure Over Difficulty

gasolsun submitted a paper 15 days ago

Ask to Distill: Learning to Synthesize Data for On-Policy Distillation

View all activity

Papers

Memory Tax: Dissecting the Net Value of Agent Memory

Your Benchmark Is an Empirical Measure Over Difficulty

View all Papers

authored a paper about 4 hours ago

On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation

Paper • 2611.05609 • Published 3 days ago • 16

submitted a paper to Daily Papers 7 days ago

Your Benchmark Is an Empirical Measure Over Difficulty

Paper • 2610.29927 • Published 16 days ago • 25

submitted a paper to Daily Papers 15 days ago

Ask to Distill: Learning to Synthesize Data for On-Policy Distillation

Paper • 2610.27450 • Published 17 days ago • 15

submitted a paper to Daily Papers 16 days ago

Competence-Based Evaluation of Logical Reasoning in Large Language Models

Paper • 2610.22894 • Published 21 days ago • 4

authored a paper 17 days ago

GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations

Paper • 2610.22708 • Published 22 days ago • 6

submitted a paper to Daily Papers 23 days ago

Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization

Paper • 2610.18738 • Published 24 days ago • 3

submitted a paper to Daily Papers 23 days ago

CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery

Paper • 2610.04851 • Published Oct 4 • 3

submitted a paper to Daily Papers 28 days ago

ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images

Paper • 2609.38680 • Published Sep 30 • 1

submitted a paper to Daily Papers about 1 month ago

Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training

Paper • 2610.07510 • Published Oct 5 • 8

submitted a paper to Daily Papers about 1 month ago

LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures

Paper • 2610.04292 • Published Oct 3 • 30

authored a paper about 1 month ago

From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation

Paper • 2610.02179 • Published Oct 1 • 7

submitted a paper to Daily Papers about 1 month ago

From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation

Paper • 2610.02179 • Published Oct 1 • 7

bx6d

submitted a paper to Daily Papers about 1 month ago

MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation

Paper • 2609.38078 • Published Sep 29 • 37

submitted a paper to Daily Papers about 1 month ago

InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation

Paper • 2610.02196 • Published Oct 1 • 29

submitted a paper to Daily Papers about 1 month ago

Hierarchical Continuous Diffusion Language Models

Paper • 2610.02193 • Published Oct 1 • 72

submitted a paper to Daily Papers about 1 month ago

ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces

Paper • 2609.33326 • Published Sep 27 • 18

submitted a paper to Daily Papers about 1 month ago

LeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning

Paper • 2609.36219 • Published Sep 28 • 2

submitted 2 papers to Daily Papers about 2 months ago

Competence-Gated Pooling of Language Models and Priors for Event Forecasting

Paper • 2609.12101 • Published Sep 10 • 2

Feature Recovery for Object Understanding After Irreversible Fire Damage

Paper • 2609.12078 • Published Sep 10 • 1

submitted a paper to Daily Papers 3 months ago

LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers

Paper • 2608.06867 • Published Aug 7 • 90