Don't Let the Model Write the YAML: Deterministic, Minimal-Diff GitOps Remediation from L…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
CoLT-Drive: Counterfactual Long-Tail Benchmarking and Knowledge-Preserving Adaptation for…
Vision-Language-Guided Pseudo-Labels for Unsupervised Domain Adaptation in Semantic Segme…
Topic Matching in the Wild: Benchmark and Lessons from Real-World ASR Transcripts
Residual Sparsification via Output Importance for Compressing Mixture-of-Experts LLMs
WHALE: A Simple Recipe for Joint Harness-Weight Optimization
QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization
ISO-RAG: Isoperimetric Noise Control for Retrieval-Augmented Generation
Distributed Implicit Harm: A Compositional Safety Blind Spot in MLLM-Based Video Moderati…
VoiceLongMemEval: Do Assistants Remember How You Sounded?
Flawed in Nature, Perfect through Evolution
TempCloze: Can Video-LLMs Identify the Missing Middle?
Do General NLP Embeddings Capture Ontological Reasoning?
Commit-first LLM judging inherits the judge's own errors
Assessing Suicide Risk in Arabic Crisis Helpline Calls: A Comparison of Arabic and Englis…
Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding
One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learning
Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturba…
Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversatio…
KItCAT: Knowledge Injection via Input Corruption for Auto-regressive Training
Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents
OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization
Life Operators: a self-evolving framework for multiscale life modelling
Medical Causal Hypothesis Verification with Large Language Models
Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Cont…
Auditing Harness Tampering in Self-Improving Agents
Electronic Navigational Chart Change Classification
3D-Consistent Multi-View Editing by Correspondence Guidance
Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided C…
ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Reca…