When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
SOAP, Muon, and Beyond: Pushing LLM Pretraining Scales
Beyond SBDD: Geometric Deep Learning in Polypharmacology and Multi-target Drug Design
Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interf…
SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aw…
EZASP - Facilitating the Usage of ASP
ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic B…
MiniCache: Reusable Program Caching with Small Model Interfaces for Efficient LLM Inferen…
Bayesian uncertainty estimation improves clinical decision making in medical AI agents
Foundation-model-guided radiogenomic discovery linking cancer genomes to cancer scans
When Does Recurrence Become an Algorithm? Convergence Selection in Weight-Tied Looped Tra…
RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring
Adaptive Multi-Horizon Reinforcement Learning
U-CFR: Uncertainty-Guided Cascade Forward Refinement for Interactive Segmentation
Transition-Related Potentials as Markers of Narrative Comprehension in Continuous EEG
Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
Surprisal Theory is Tautological (without Rational Grounding)
MIRROR: Learning from the Other View for Multi-Modal Reasoning
Neural solutions of coupled ghost and gluon Dyson--Schwinger equations in Landau gauge
UnDA: Unpaired Domain Alignment for Cross-Modal Knowledge Transfer in Medical Imaging
Windowed-MTP: Removing the Full-Context Draft-KV Tax at Million-Token Context
From Resource Flow to Executable Tests: Petri-Net-Guided LLM Test Generation for Concurre…
Texture++: Elevating 3D Asset Texture Resolution with a Region-Aware Diffusion Model
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle a…
Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure,…
Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation
Agentic coding without the cloud: evaluating open-weight large language models on longitu…
Error Certificates for KV-Cache Eviction via Randomized Design
Future Rendering $\neq$ Future Surface: A Benchmark and Dataset for Dynamic Surface Recon…
Detecting LLM-Generated Tokens in Human--LLM Coauthored Text