University of Illinois at Urbana-Champaign

university

Verified

https://illinois.edu

AI & ML interests

None defined yet.

Recent Activity

yujiazheng submitted a paper about 3 hours ago

DSReg: Provably Recovering Individual World Latents without Reconstruction

qiusizhan submitted a paper 1 day ago

Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training

zsqzz authored a paper 3 days ago

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

View all activity

Papers

DSReg: Provably Recovering Individual World Latents without Reconstruction

Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems

View all Papers

submitted a paper to Daily Papers about 3 hours ago

DSReg: Provably Recovering Individual World Latents without Reconstruction

Paper • 2610.09457 • Published 2 days ago • 2

submitted a paper to Daily Papers 4 days ago

Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems

Paper • 2609.39050 • Published 9 days ago • 17

submitted a paper to Daily Papers 8 days ago

Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training

Paper • 2609.40111 • Published 9 days ago • 50

submitted a paper to Daily Papers 8 days ago

Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI

Paper • 2609.38143 • Published 10 days ago • 84

submitted 2 papers to Daily Papers 9 days ago

Pretraining Transformers with Quantized Softmax in Attention

Paper • 2609.33591 • Published 12 days ago • 6

Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel Acceleration

Paper • 2609.33586 • Published 12 days ago • 4

submitted a paper to Daily Papers 9 days ago

Learning from Teacher Continuations at Student States

Paper • 2609.36246 • Published 11 days ago • 40

submitted 2 papers to Daily Papers 24 days ago

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

Paper • 2609.12101 • Published 29 days ago • 2

Feature Recovery for Object Understanding After Irreversible Fire Damage

Paper • 2609.12078 • Published 29 days ago • 1

DCTR

submitted a paper to Daily Papers 28 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 487

submitted a paper to Daily Papers about 1 month ago

Evaluating the Hidden Costs of Personalization in Large Language Models

Paper • 2608.28833 • Published Aug 28 • 30

authored 9 papers about 2 months ago

AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses

Paper • 2608.12307 • Published Aug 12 • 118

ACCORD: Action-Conditioned Contextual Grounding for Language Agents

Paper • 2606.16432 • Published Jun 15

Trimming the Long-Tail of Visual World Modeling Evaluation

Paper • 2606.24256 • Published Jun 23 • 41

MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models

Paper • 2605.28009 • Published May 27 • 3

PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

Paper • 2606.22388 • Published Jun 21 • 96

On Effectiveness and Efficiency of Agentic Tool-calling and RL Training

Paper • 2606.00135 • Published May 28 • 1

Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary

Paper • 2506.00886 • Published May 8

Brick-Composer: Using MLLMs for Assembly with Diverse Bricks

Paper • 2606.05445 • Published Jun 3 • 8

AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints

Paper • 2606.05622 • Published Jun 4 • 45