DAIS: Dependency-Aware Intermediate QA Supervision for Complex Reasoning
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
A Controlled Study of Attention-Only Transformers
Semantic Cooperative Games for Contribution Attribution in LLM-Based Multi-Agent Systems
Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads
SAAG: Structured Agent Assessment and Grounding
Intelligence from Learnable Novelty
Analytic Distribution of Classifier-Free Guidance for Schedule Design
An Exploratory Analysis of Pain Localization via Explainable Computational Modeling
ReFace: Reorganizing Facial Spatiotemporal Representations for Improved Pain Assessment
How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes f…
PhenSPINE: A Standardized Benchmark for Spine Pathology Diagnosis
NavVerse: Benchmarking Indoor-to-Outdoor Embodied Navigation in Continuous Robot Simulati…
Anatomy of a Sound Neural Reasoner: One-Shot Amortization, First-Pass Poisoning, and Sear…
Online Optimization of Difference-of-Convex Compositions with Smooth Mappings
The State of Simulation for Physical AI: An Overview
RELTA-SGLD: Relative-Growth Localized Taming for Nonconvex Stochastic-Gradient Langevin L…
🔬Causal Models Need Causal Data - Xaira’s X-Cell model for Drug Discovery (Bo Wang & Ci C…
Equilibrium Causal Games: Separation, Identification, and the Identifiability of Cyclic L…
This Former Intel CEO Wants to Jumpstart Moore’s Law With Light
Detect Early, Escalate Rarely: Anytime Detection of AI-Generated Video from the Compresse…
ExpertVerse: A General-Purpose Benchmark for Expert-Level Reasoning in Knowledge-Intensiv…
OmniReasoner: Thinking with Long Audio-Video via Native Tool Use
CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents
1-Lipschitz Neural Networks on Hadamard Manifolds
ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling
No Training, Better Flights: Test-Time Scaled VLMs for UAV Navigation
GUIDED Network-Agnostic Feature Initialization for Spatial Transferability in GNN-based M…
PathAgentBench: Benchmarking Evidence-Seeking Vision-Language Models on Whole-Slide Patho…
Prompt Design at Scale: How Format, Instruction Count, and Context Length Shape Instructi…
Exploring self-distilled reasoning for supervised fine-tuning with Amazon Nova