Evaluating Vision-Language Models as a Zero-Shot Learning Alternative to You Only Look On…
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories
Using embeddings to predict spoken word duration and pitch in Mandarin monosyllabic words
Finance and Tech Cut 28,000 Jobs Monthly as AI Takes Hold
OpenAI Proposes Giving 5% Stake to US Government: FT
OpenAI floats giving Trump administration 5 percent cut of AI boom
Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Pr…
Probabilistic Low-Voltage Peak Load Forecasting with Time Series Foundation Models Evalua…
Towards a Phonology-Informed Evaluation of Multilingual TTS
NeoMap: Training-free Novel-View Synthesis from Single Images and Videos
Autorelevance function and other feature relevance measures for univariate time series
LiZAD: A Lightweight Zero-Shot Anomaly Detection Framework for Industrial Manufacturing
Hybrid quantum-classical neural network for sentiment analysis
Meta Is Charging a Subscription for Smart Glasses Features. Welcome to the New Era of Con…
AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanati…
OpenAI reportedly wants all AI companies to give the US government a stake in their busin…
Rethinking Complexity Metrics for LLM-Integrated Applications: Beyond Source Code
Rethinking Post-Hoc Calibration in Semantic Segmentation
Starbucks is paying baristas to make TikToks. Expect more brands to follow.
FoundDP: Revisiting Weak Disparity Observability in Dual-Pixel Depth Estimation
Spec-AUF: Accept-Until-Fail Training under Train-Inference Misalignment for Masked Block …
Diversity-aware View Partitioning for Scalable VGGT
Learning the Supports for Categorical Critic in Reinforcement Learning
SAB-LVLM: Significance-Aware Binarization for Large Vision-Language Models
An Exploratory Study on LLM-Generated Code and Comments in Code Repositories
Safety Targeted Embedding Exploit via Refinement
Evaluating Chunking Strategies for Retrieval-Augmented Generation on Academic Texts
Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction
Adaptive Group-Based Counterfactual Explanations for Time-Series Rehabilitation Data
Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling