The Surprising Effectiveness of Approximate Value Iteration in Self-Play
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Canonical Color as a Lens into Concept Decodability in Vision Encoders and VLMs
Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course
Application of curiosity driven exploration methods for hardware interference identificat…
When Can One Obtain Certificates of Optimality Using Positivstellensaetze?
SkillAdam: Stable and Efficient Skill Evolution for Agents
SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for R…
AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems
A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation
Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and…
Personalizing LLM Agent Memory Using Biometrics
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
A Generalization of Amari's Bayesian Duality
MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive M…
LEBGen: An LLM-Enhanced Bayesian Network Framework for Few-Shot Travel Survey Data Genera…
GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initi…
CLAMP: Constrained Decoding for Vision-Language Embodied Planning
Damage-Aware Bandit Pruning for Vision and Language Transformers
DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aw…
When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agen…
TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Ac…
Omni Interaction Agent Technical Report
SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale
Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampli…
zScore-N: A Neural Network for On-Chain Wallet Reputation Scoring
Fewer yet critical: Reducing Redundant Token Dependencies for Transformer-based Time Seri…
Qiushi Engine on AstaBench E2E-Bench-Hard
Agentic ML Exploration (A-MLE) for Ads Ranking
It Is Not My Code Anymore