Visual Framing for News Stance Detection via Image Generation
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
DualStake: Dual-Path Confidence Calibration in Deep Research Agents
Semantic-Guided Multimodal Preprocessing for Vision Transformer-Based Clear Cell Renal Ce…
One Prompt Is Enough: Watermark Laundering Through Foundation Image Models
Does Fault Localization Beat a Fresh Attempt? A Placebo-Controlled Study of Test-Guided C…
Benchmarking Vision-Language Models for Automated Pathology Diagnosis and Report Generati…
Beyond the Image Plane: World-Grounded Queries for Multi-Object Tracking
GeoPAR: Large-Scale Multi-Agent Combinatorial Optimization with Geometry-Guided Parallel …
Predicting Program Exit Code with LLMs and Programming Language Semantics
WiseSpec: Requirements-Driven Agents for Code Generation
SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
Solaris: Towards Interfaces That Are Generated, Not Coded
The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space
The Safeguard Worked. Is the LLM System Safer?
EEG-VID: Task-Guided Latent Predictive Pretraining for EEG Decoding and Assistive Target …
Towards Effective Structured Context Modeling for Conversational Recommender Systems via …
SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verificat…
ADGNet: Asymmetric Dual-text Guided Network for Infrared Small Target Detection
Optimizing Byzantine Node Placement in Decentralized Federated Learning
Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Hete…
Disclosure-Gated User Simulation for Companion-Agent Evaluation
Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Mode…
Efficiently Estimating Optimal Hyperparameter Scaling Laws through Power-Law Entropy Sear…
Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy
Assessing Alignment and Stability of Feature Importance Explanations via Weight of Eviden…
Lingua Franca or Probing Artifact? Rethinking Latent Language in Multilingual LLMs
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
MADS: A Multiview Acoustic Descriptor Set Beyond Standard Spectral Summaries
Replacing Training with Memory: Listwise Selection for Text-to-SQL
Intelligent Edge Computing