EdgeLM: Edge Demonstrations for Language Models' Table Understanding
Explorar
Noticias de IA
21861 elementos — filtrados, clasificados y sin duplicados
Image Classification Using CNN-QNN Hybrid Model with Optimized Correlated Features
The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Sc…
HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework …
Looking in the Mirror: Introspecting Side-Effect Misalignments Induced by Fine-Tuning
Right Reset: Chunking by Prefix Removal
An Analysis and Implementation of Seam Carving for Content-Aware Image Resizing
Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content …
Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-…
Open-weight AI models are catching up to the frontier. The safety gap remains.
SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation
TS2TabPFN: Time Series Classification and Extrinsic Regression through Feature Extraction…
ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs
SocietyBench: Forecasting Counterfactual Social-World Evolution
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input P…
Separating quantum circuits from classical LLMs
UniEvo-RS: Omni-Prompt Unified Remote Sensing Segmentation with Representative Exemplar-D…
MuRA: Multi-Rank Adaptation for Efficient and Effective Test-Time Vision-Language General…
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
CPrefix: A Combinatorial Tensor Framework for Structured Discrete Color Mappings
Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding
FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synt…
Autoreflection: How Agentic Strange Loops Turn Human Culture into AI Infrastructure
Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowle…
Can LLMs Test Terminal User Interfaces?
Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improve…
SAT-Edge-Agent: Hardware-in-the-Loop Edge-Agent Orchestration for Onboard Satellite Intel…
When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Coupling Diagnostic fo…
Attention is Case-Sensitive