Not all Negation Cues are Equal: Affixal Negations Yield Better Negation Understanding
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Uncertainty-Aware Calibrated Clinical Text Classification with Large Language Models
Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from A…
Adaptive Phase-Switching for Communication-Efficient Federated LoRA Fine-Tuning
CapGeo-Bench: Decoupling Visual Perception from Reasoning and Evaluating Geometric Unders…
Mesh-based Super-resolution of Multiscale Detonation Flows with Graph Transformers
DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis
Hardware-Aware Learned Representation Compression for Distributed In-Sensor Vision
Mizan: A National Benchmark for Evaluating Large Language Models on Iraqi Arabic and the …
Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot Coll…
Efficient On-Device Agents via Adaptive Context Management
Rolling Day-Wise Mortality Prediction in Critically Ill Patients With AKI on CRRT Utilizi…
Talking to Me or Someone Else? Rethinking Talk-to-Me Detection in Egocentric Videos
A New Transformer-Based Approach for Audio-Based Kinship Verification and a New Uncontrol…
Has Scientific Talent Shifted from Depth to Breadth?Evidence across Papers, Knowledge Inp…
NeuroProlog: Multi-Task Fine-Tuning for Neurosymbolic Mathematical Reasoning via the Cock…
Lightweight Generalized DeepFake Face Detection with WAVIE: Wavelet Augmented Vision Inte…
TyPatch: Transforming Patches into Typestate Rules for Kernel Bug Detection
LePlanner: An Iterative Amortized Controller For World Models
HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Re…
NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass
Follow the Geometry, Not the Model: Cold Start Semi-Supervised Learning
AlgoRAG: Retrieval-Augmented Generation for Theoretical Computer Science Education -- A C…
Diagnosing Temporal Misalignment in Multichannel Time-Series Classification with Minimum …
MANE: A Multi-Path Adaptive Network for Edge Onloading of Deep Neural Networks
WaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kron…
Calibrating Interpretability Instruments Before Trusting Their Verdicts
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions…
TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root …
Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Mode…