AgentRewind: Recoverable Execution for Long-Horizon LLM Agents
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments
Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports
Shift Aware Transfer Learning with Adaptive Dual-Encoder Fusion for PM Forecasting in Dat…
Participatory Moral AI Is Not Neutral: The Invisible Hand of Developers
A Hybrid LLM-Based Framework for Automated Security Annotation Generation in Business Pro…
GBU-Palm: A Multimodal Video Dataset and Benchmark for Palm Presentation Attack Detection
Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systemati…
From Style Replication to Style Exploration: Enabling Art Style Exploration with Analyze-…
When Personal Memory Has No Single Answer: Evaluating LLM Agents under Irreducible Confli…
AI Research Preference Models
Residual Dominance as a Structural Account of Last-Item Reliance in Causal Self-Attention…
Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems
Context Aware AI Assistant and AR Interface for Lunar Extravehicular Activity (EVA) Proce…
Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Ta…
$R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets
AdROD: HyperNetwork-based Adversarially Robust Object Detection for Autonomous Driving
Multi-scale Decomposed Convolution Refinement Network for Visible-Infrared Person Re-Iden…
ReRef-3D: A Benchmark for Spatial Referring Expression-Guided 3D Scene Rearrangement
Spatial Temporal Synergy: Balancing Change and Invariance in Text Driven 3D Human Motion …
Operator-Theoretic Generalization Bounds for Multitask Deep Learning
ALPS: Measuring Valid Creativity in Large Language Models with Mathematical Construction
Fiber Fingerprints of Hidden Learning-State Dynamics
BagShift: Measuring How Patch Selection Changes the Evidence Seen by Whole-Slide MIL
Augmenting Text to Increase Translation Difficulty
Noesis: Bidirectional Graph-RAG with Adaptive Parallelism and Cross-Knowledge-Base Semant…
Red queen hypothesis – A new way forward for self-improving AI
Dense Expands, Sparse Anchors: Channel-Asymmetric Query Expansion for Hybrid Retrieval
Pricing the Risk of Runtime Compression: Anytime-Valid Admission and a Served-Output Law …
PWLR: Pairwise Witness Local Rejection for Boundary-Aware Out-of-Distribution Detection