Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems
AI Evaluation Should Require Standardized Item-Level Data Releases
VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation
Scaling-Aware Adapter for Structure-Grounded LLM Reasoning
Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memor…
Human Decision-Making with Persuasive and Narrative LLM Explanations
Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot
CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Ima…
DualMem: Bypassing the Objectness Bottleneck for Calibrated Unknown-Stream Filtering in O…
EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video…
Cost-Effective Model Evaluation with Meta-Learning
DrawVideo: Generating Long Video from Storyboard Keyframe Sketches
Multimodal Distribution Matching for Vision-Language Dataset Distillation
Automated Random Embedding for Practical Bayesian Optimization with Unknown Effective Dim…
Learning Individual Dynamics from Sparse Cross-Sectional Snapshots
SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
Atom-level Protein Representation Learning Improves Protein Structure Prediction
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
CHASD: Language Increment-Calibrated Contrastive Decoding against Hallucination in LVLMs
Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition
Convergence Without Understanding: When Language Models Agree on Representations but Disa…
More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Det…
When Good Equations Get Bad Scores: Improving Symbolic Regression Through Better Paramete…
6G Communication Networks Enabling Embodied Agents: Architecture and Prototype
CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test
FastKernels: Benchmarking GPU Kernel Generation in Production
Adaptive Mass-Segmented KV Compression for Long-Context Reasoning
DiLaDiff: Distilled Latent-Augmented Diffusion for Language Modeling
EMA-Nesterov: Stabilizing Nesterov's Lookahead for Accelerated Deep Learning Optimization