Leak-Resistant Unlearning: A New Benchmark for Evaluating Multi-Hop Reasoning Consistency…
Explorar
Noticias de IA
29351 elementos — filtrados, clasificados y sin duplicados
RESPClinBench: Benchmarking Multimodal Clinical Decision-Making and Longitudinal Disease …
AFD-Ledger: Deployment Provisioning for Attention--FFN Disaggregation
Moonshot Backer Monolith Seeks to Raise $500 Million in New Fund
GDM leadership reset
Infineon Revenue Forecast Beats as AI Power Chip Demand Rises
Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Medi…
Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Mod…
A Counterexample to Fourier Alignment in Single-Neuron Modular Addition
Zero-Mem: Zero-Token Memory Operations for LLM Agents
Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes
Generative Optimization for Incentivized Advertising with Global Level Constraints
Long-term Traffic Scene Prediction via Polynomial Representations in Autonomous Driving
Secure AI Watermarking Framework for IP Protection in Multi-Tenant Cloud Platforms
SAGE: Semantic Explainability of Attention-Based Survival Models in Computational Patholo…
Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MC…
Cross-Anesthetic ECoG State Decoding Fails at the Decision Threshold, Not the Representat…
Leveraging System-Level Observations to Inform Bayesian Learning of Model Parameters for …
SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation
UniNav: A Unified World-Action Diffusion Model for Visual Navigation
A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation
STREAM-VAE: Dual-Path Routing for Slow and Fast Dynamics in Vehicle Telemetry Anomaly Det…
Studying, Identifying, and Fixing Hidden Technical Debt in AI-Intensive Cyber-Physical Sy…
Robust Counterfactual Policy Optimisation via Nondeterministic Causal Models
Separating quantum circuits from classical LLMs
Evading Chain-of-Thought Monitoring Through Model Poisoning
Can LLMs Test Terminal User Interfaces?
One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learning
Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds
Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning