Portada · pág. 7

← primera página

Implicit Reasoning in Transformers: Bridging the Compositionality Gap in GPT-2-like Models
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Distilling the Shape of Uncertainty: What On-Policy Distillation Learns and How to Predict It
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Representation Complexity Along Learning Trajectories: Trading Width for Precision and Time
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Reinforcement Learning for the Game of Balatro: A Fast Simulator and Two-Policy Training Approach
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
When Does Closed-Loop Curriculum Adaptation Help GRPO? An Analysis on Countdown
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
HERA: Assessing an Autonomous Agent for Quantum Device Measurement
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Tactus: Tactile & Pose Sensing Glove for Natural Dexterity Data Collection
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Generating Critic-Guided Synthetic Experience in Latent World Models
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
PCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Clean Sheets and Checkpoints: Evidence Complexity for Certifying Sequential Agent Risk
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
REALM: Identifying Minimal Task Assets for LLM Agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
PRISM: Personalized Item Representations in User History
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
EmbodiExp: Compositional Experience Transfer for Embodied Agents
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Where Position Matters: Profiling-Guided Layer-Wise RoPE Allocation in Transformers
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
There Is No Free Lunch in RLVR: Every pass@1 Gain Has a pass@k Price
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Learning to Bound: Monotonic, Calibrated Neural Upper Bounds for MPE Inference
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Telling Is Not Seeing: Textual Personas Rarely Make Vision-Language Models Answer Like the People They Describe
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
RetroChessBench: A Benchmark for Reconstructing and Proving Chess Histories
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Semantic Mismapping in Generalized Category Discovery: Evaluation and Mitigation
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
What Makes Medical Examination Items Difficult? Using Large Language Models to Explore Patterns Associated With Empirical Item Difficulty
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Learning to Formulate: Agentic Hardware-Software Co-Design of AI Infrastructure through Progressive Optimization and Verification
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
UMI-Live for In-The-Wild Bimanual Robotics Data Collection
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
OPERA: OPamp Design by an Expert-Taught Reasoning Agent, from Specifications to Layout
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
SymKL: A Unified Representation-Space Measure of Signal Degradation
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Safe Multi-Objective Reinforcement Learning: Zero Constraint Violation and Primal-Averaging Convergence
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Well-Specified and Well-Tested? Assessing SWE-bench-Style Datasets with a Self-Evolving Agent
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Sparse Fine-Tuning for Parameter-Efficient Adversarial Training
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Integrating Heterogeneous Echocardiography AI Outputs in Language Space: Learnable Late Fusion with a Supervised LLM
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Agent-Wise Test-Time Normalization for Camera-Based Cooperative Perception with Corrupted Collaborators
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Raincheck: Deferred Multimodal Prefill for Efficient Multi-Turn MLLM Inference
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
LLM Agent-Based Design of RISC-V CPUs with FPGA-in-the-Loop Evaluation
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Generative artificial intelligence prompting strategies among Chinese university students across academic tasks
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Red-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Data Provenance and Ethics in the Curricula of U.S. Health AI Education Programs
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Intrinsic Distribution Matching
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Where Do Vision Language Models Fail at 3D Reasoning?
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Rebuilding a Field's Open-Problem Catalog from the Literature: A Two-Layer Knowledge Graph, and Why Status Must Stay Proposed
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Event-SAMA: Language-Grounded Video Object Segmentation on Neuromorphic Event Streams
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Can AI Agents Interface Clinicians and Complex Models?
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Practical Assessment of Agentic Systems in Acoustics
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle
Sandman: Building and Operating Sandboxes for Agentic Reinforcement Learning on Shared Kubernetes
arXiv cs.AIarxiv.orgAgregado: 31/10/2026, 7:01:09Publicado: 31/10/2026, 4:00:00detalle