Worker Disagreement Reveals Sharp Directions in Local SGD
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Mahalanobis PatchCore: Covariance-Aware and Streaming-Compatible Industrial Anomaly Detec…
Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
Turning Video Models into Generalist Robot Policies
Score Based Error Correcting Code Decoder
LASER: Learning Active Sensing for Continuum Field Reconstruction
Compositional Consistency-Guided Decoding for Three-Way Logical Question Answering
Causal Direct Preference Optimization for Distributionally Robust Generative Recommendati…
The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling
The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic V…
Differential syntactic and semantic encoding in LLMs
Fine-Tuned LLM as a Complementary Predictor Improving Ads System
HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex…
Optimal and Diffusion Transports in Machine Learning
From Detection to Mechanism: Cross-Attention Graph Neural Networks Enable Drug-Drug Inter…
MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryM…
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process…
Probability-Entropy Calibration: An Elastic Indicator for Adaptive Fine-tuning
Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Soko…
STFlow: Data-Coupled Flow Matching for Geometric Trajectory Simulation
GradientStabilizer:Fix the Norm, Not the Gradient
Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM A…
Text2Model: Modeling Copilots for Text-to-Model Translation
DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision…
Heterogeneous Causal Discovery of Repeated Undesirable Health Outcomes
Reverse Probing: Supervised Token-level Uncertainty Quantification for Large Language Mod…
Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking