Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?
Paper • 2610.32046 • Published • 19
AI & ML interests
None defined yet.
Recent Activity
View all activity
Xuandong
authored 13
papers about 4 hours ago
Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
Paper • 2605.30614 • Published
Invisible Image Watermarks Are Provably Removable Using Generative AI
Paper • 2306.01953 • Published
Humanity's Last Exam
Paper • 2501.14249 • Published • 79
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation
Paper • 2609.04298 • Published • 1
Learning to Follow In-Context Watermark Instructions via Self-Distillation
Paper • 2608.29030 • Published
MatrAIx: Simulating the World with 8.3 Billion Persona Agents
Paper • 2608.04205 • Published • 60
VIMPO: Value-Implicit Policy Optimization for LLMs
Paper • 2606.20008 • Published
Self-Sovereign Agent
Paper • 2604.08551 • Published • 5
MemFail: Stress-Testing Failure Modes of LLM Memory Systems
Paper • 2605.26667 • Published
Auditing Agent Harness Safety
Paper • 2605.14271 • Published • 55
DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards
Paper • 2605.08441 • Published • 1
Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement
Paper • 2402.11436 • Published
stneng
updated a
dataset about 2 months ago
yujinyujin9393
updated a
dataset 3 months ago
ncrispino
updated a
dataset 3 months ago
stneng
published a
dataset 4 months ago
Xuandong
submitted a
paper to Daily Papers 6 months ago
ncrispino
published a
dataset 7 months ago
Improve model card with paper summary and code links
#1 opened 8 months ago
by 
nielsr