See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents
Paper • 2606.13594 • Published • 3 •
3
Noah
noahml
AI & ML interests
None yet
Recent Activity
commentedon a paper about 2 hours ago
See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents commentedon a paper about 2 hours ago
Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents commentedon a paper about 2 hours ago
Flash-GMM: A Memory-Efficient Kernel for Scalable Soft ClusteringOrganizations
None yet
commented 5
papers about 2 hours ago
Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents
Paper • 2606.13174 • Published • 2 •
3
Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering
Paper • 2606.10896 • Published • 3 •
3
PianoKontext: Expressive Performance Rendering from Deadpan Context
Paper • 2606.12282 • Published • 1 •
3
The Cold-Start Safety Gap in LLM Agents
Paper • 2606.07867 • Published • 2 •
3
commented 5
papers about 20 hours ago
TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search
Paper • 2606.11662 • Published • 10 •
3
Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models
Paper • 2606.11409 • Published • 8 •
3
MiniMax Sparse Attention
Paper • 2606.13392 • Published • 113 •
4
High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation
Paper • 2606.12575 • Published • 8 •
3
Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior
Paper • 2606.12730 • Published • 5 •
3
commented 5
papers 2 days ago
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Paper • 2606.11817 • Published • 17 •
5
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models
Paper • 2606.12412 • Published • 16 •
3
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
Paper • 2606.11119 • Published • 17 •
3
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
Paper • 2606.08063 • Published • 74 •
3
VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
Paper • 2606.12243 • Published • 29 •
4
commented 5
papers 3 days ago
WorldOlympiad: Can Your World Model Survive a Triathlon?
Paper • 2606.11129 • Published • 30 •
3
In-Context Multiple Instance Learning
Paper • 2606.06458 • Published •
3
PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models
Paper • 2606.09697 • Published • 6 •
4
UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors
Paper • 2606.11131 • Published • 5 •
3
Redesign Mixture-of-Experts Routers with Manifold Power Iteration
Paper • 2606.12397 • Published • 83 •
4