F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Counterfactual Explanations for Hypergraph Neural Networks
Krause Synchronization Transformers
Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards
Towards Evaluation Engineering: An Empirical Study of ML Evaluation Harnesses in the Wild
Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environ…
CARL-CXR: Continual Adapter-Based Routing for Task-Unknown Chest Radiograph Classification
MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
Non-Invasive Reconstruction of Intracranial EEG Across the Deep Temporal Lobe from Scalp …
MultiPUFFIN: A Multimodal Domain-Constrained Foundation Model for Molecular Property Pred…
Topology-Driven Transferability Estimation of Medical Foundation Models for Segmentation
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
Measuring the Depth of LLM Unlearning via Activation Patching
UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Tasks
PowerFlow: Unlocking the Dual Nature of LLMs via Principled Distribution Matching
Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal M…
Adversarial Error Correction for Visual Autoregressive Generation
Temporal Dropout Risk in Learning Analytics: A Harmonized Survival Benchmark Across Dynam…
AEROS: A Single-Agent Operating Architecture with Embodied Capability Modules
UniRank: End-to-End Domain-Specific Reranking of Hybrid Text-Image Candidates
Beyond Static Uncertainty: Modeling Temporal Uncertainty Dynamics for Probabilistic Time …
Beyond the Aggregation Dilemma: Prior-Retaining Decoupled Learning for Multimodal Graphs
Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing
Depth Registers Unlock W4A4 on SwiGLU: A Reader/Generator Decomposition
Federation over Text: Insight Sharing for Multi-Agent Reasoning
Motion-Compensated Weight Compression
VILAS: A VLA-Integrated Low-cost Architecture with Soft Grasping for Robotic Manipulation
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Gener…
ESIA: An Energy-Based Spatiotemporal Interaction-Aware Framework for Pedestrian Intention…
Talking Slide Avatars: Open-Source Multimodal Communication Approach for Teaching