Can Vision-Language Models Solve the Shell Game?
Paper • 2603.08436 • Published • 39 •
4
Noah
noahml
AI & ML interests
None yet
Recent Activity
commentedon a paper about 1 hour ago
Can Vision-Language Models Solve the Shell Game? commentedon a paper about 1 hour ago
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement commentedon a paper about 1 hour ago
Small Vision-Language Models are Smart Compressors for Long Video UnderstandingOrganizations
None yet
commented 5
papers about 1 hour ago
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
Paper • 2603.06333 • Published • 1 •
3
Small Vision-Language Models are Smart Compressors for Long Video Understanding
Paper • 2604.08120 • Published • 20 •
3
Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding
Paper • 2604.08537 • Published • 9 •
3
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Paper • 2604.11544 • Published • 4 •
3
commented a
paper about 7 hours ago
commented 5
papers about 8 hours ago
SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
Paper • 2604.11716 • Published • 5 •
3
ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation
Paper • 2605.28293 • Published • 78 •
3
Models That Know How Evaluations Are Designed Score Safer
Paper • 2605.28591 • Published • 4 •
5
Self-Improving Language Models with Bidirectional Evolutionary Search
Paper • 2605.28814 • Published • 50 •
3
CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation
Paper • 2605.25378 • Published • 48 •
2
commented 6
papers 1 day ago
Recursive Multi-Agent Systems
Paper • 2604.25917 • Published • 273 •
5
Representation Fréchet Loss for Visual Generation
Paper • 2604.28190 • Published • 32 •
2
Let ViT Speak: Generative Language-Image Pre-training
Paper • 2605.00809 • Published • 33 •
3
DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes
Paper • 2605.28421 • Published • 43 •
4
Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders
Paper • 2605.27354 • Published • 12 •
3
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization
Paper • 2605.28109 • Published • 17 •
3
commented 3
papers 3 months ago