WorldOlympiad: Can Your World Model Survive a Triathlon?
Paper • 2606.11129 • Published • 29 •
3
Noah
noahml
AI & ML interests
None yet
Recent Activity
commentedon a paper 35 minutes ago
WorldOlympiad: Can Your World Model Survive a Triathlon? commentedon a paper 35 minutes ago
In-Context Multiple Instance Learning commentedon a paper about 7 hours ago
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language ModelsOrganizations
None yet
commented 2
papers 35 minutes ago
commented 5
papers about 7 hours ago
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
Paper • 2606.09697 • Published • 5 •
4
UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors
Paper • 2606.11131 • Published • 4 •
3
Redesign Mixture-of-Experts Routers with Manifold Power Iteration
Paper • 2606.12397 • Published • 74 •
2
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Paper • 2606.11926 • Published • 67 •
3
On Subquadratic Architectures: From Applications to Principles
Paper • 2606.12364 • Published • 20 •
2
commented 5
papers 1 day ago
OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning
Paper • 2606.08572 • Published • 13 •
3
A Geometric Account of Activation Steering through Angle-Norm Decomposition
Paper • 2606.06735 • Published • 20 •
3
Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders
Paper • 2606.07473 • Published • 12 •
3
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
Paper • 2606.11176 • Published • 36 •
2
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Paper • 2606.09730 • Published • 49 •
3
commented 8
papers 2 days ago
Direct 3D-Aware Object Insertion via Decomposed Visual Proxies
Paper • 2606.06601 • Published • 26 •
5
UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs
Paper • 2606.06622 • Published • 19 •
3
SwiftVR: Real-Time One-Step Generative Video Restoration
Paper • 2606.09516 • Published • 14 •
4
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Paper • 2606.06361 • Published • 14 •
3
Augmenting Attention with Exponentially Decaying Memory Improves Query-Aware KV Sparsity
Paper • 2605.28640 • Published •
4
Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short
Paper • 2606.09380 • Published • 7 •
3
SwiftVR: Real-Time One-Step Generative Video Restoration
Paper • 2606.09516 • Published • 14 •
4
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
Paper • 2606.06087 • Published • 59 •
5