Capability Is Not Propensity: Measuring Pressure-Robust Cooperative Behavior in Civic LLM…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
How Simple Can It Get? From Interpretable Equations to Readable Rules for Financial Decis…
Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questi…
Calling the Bluff: Detecting Ever-Shifting Harmful Chat Dialogue via Ordered Reasoning Ch…
Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Mode…
Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
LibraSpec: Dynamic Diffusion-Based Speculative Decoding via Marginal-Gain-Driven Optimiza…
Enhancing Knowledge Tracing through Leakage-Free and Recency-Aware Embeddings
Open-World Semantic Segmentation with Sensitivity Modeling
Dynamic gain neuromodulation attenuates the stability gap under joint training
MateInfoUB: A Real-World Benchmark for Testing LLMs in Competitive, Multilingual, and Mul…
PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distill…
MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks
AquiLLM: An Architecture for Supporting Tacit Knowledge Capture in Research Groups
MELLON - Multimodal Enhanced LLM for Online Navigation
Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction
From Alignment to Synthesis Contrastive Volumetric Grounding for Text-to-CT Generation
A Combined Feature-Based Framework for Disguise and Spoofing Detection in Face Recognitio…
TLDChoiceNet: Quantitatively Choosing a Transfer Learning Dataset
Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Thre…
Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmen…
Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical …
Do Time-Series Forecasters Use the Right History: Recoverability, Recovery, and Functiona…
GeoSeg-OV: Bridging Geospatial Gaps with Structural Guidance for Open-Vocabulary Remote S…
VisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback?
Automatic Field-of-View Adjustment for a View-Expansive Microscope via LSTM-Based Gaze an…
FormStruct-Bench:A Hierarchical and Diagnostic Benchmark for Table-Form Document Structur…
A Single Atom in Front of a Mirror is a Universal Reservoir Computer
Fisher8: Stabilizing Neural Heteroscedastic Regression via Output-Layer Fisher Geometry
CasDeblurGS: Cascaded 2D-to-3D Multi-View Consistency for 3D Gaussian Splatting from Two …