Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Re…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective
A Semantic Model of Genetic Evidence: A Step Toward Bridging the Basic-Science-Clinic Gap
Pitch-class Steering for Diffusion-based Music Generation via Latent-space Probes
Shared circuits predict whether LLMs generalize across formats in arithmetic reasoning
Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling bi…
REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Conc…
X-VC: Zero-shot Streaming Voice Conversion in Codec Space
HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward…
GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Ex…
When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Mod…
Beyond Aggregate Scores: Behavioral Correctness Assumptions for Assessing Reference-Based…
TeleTables: A Benchmark for Large Language Models in Telecom Table Interpretation
GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction
Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D Detection
Cross-Task Generalization Between Understanding and Generation in Unified Vision-Language…
AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Traj…
Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language …
GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And…
Role-Aware Artificial Intelligence Across Augmentation and Automation in Human-Machine Sy…
AI-Powered CPS-Enabled Vulnerable-User-Aware Urban Transportation Digital Twin: Methods a…
SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection
Reflection-aware Generative Novel View Synthesis
RegionFed: Federated Learning for Personalized Query Understanding in Heterogeneous Retai…
RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training
MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolu…
YOLO with Kolmogorov-Arnold networks and vision-language foundation models for interpreta…
GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity
Beyond Stationarity in Time Series: Discovering Causal Structures and Latent Regimes via …