Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
When Can We Trust Early Warnings? Leakage-Excluded Early Outcome Prediction from LMS Inte…
On the Benefits of Free Exploration for Regret Minimization in Multi-Armed Bandits
StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Str…
Broadband Hyperspectral 3D Imaging using Dispersed Structured Light
DeGRe: Dense-supervised Generative Reranking for Recommendation
Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains
The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible
CMAP: Cross-Modal Adaptive Prompting for Multi-Domain Task-Incremental Learning
AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization
How Far Has AI Come in Liver Fibrosis Staging? A Large-Scale Real-World Dataset and Bench…
AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution
Learning Permutation from Structure Without Supervision
TopoAlign: Topology-Aware Visual Representation Alignment
StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs
Guided Flow Matching for Forward and Inverse PDE Problems with Sparse Observations: Algor…
Full-4D: Generating Full-Scope 4D Scenes from a Single-View Video
Accelerated Dynamic Importance Weighting with Versatile Divergence-Minimizing Estimators
EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Mo…
JacQuant: STE-Free Quantization-Aware Training via Learned Jacobian Surrogates
From Simulation to Enaction: Post-trained language models recognize and react to their ow…
SomaliBench Eval: Measuring English-to-Somali Refusal Gaps in Open-Weight Language Models
Capture-Calibrate-Coach: A Graph-Based Framework for Knowledge Monitoring Estimation and …
IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
Bridging Data and Physics: A Graph Neural Network-Based Hybrid Twin Framework
The AI-Native Large-Scale Agile Software Development Manifesto
ReCoVer: Resilient LLM Pre-Training System via Fault-Tolerant Collective and Versatile Wo…
Classical State Preparation for Variational Quantum Algorithms via Reinforcement Learning
R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivot…