Mind Which Bird You Favour: Parameterizing Adequacy-Fluency Balance in Meta-Evaluation of…
Browse
AI News
27413 items — filtered, classified, deduplicated
The Stochastic Deputy: Structural Tenant Isolation for Tool-Using LLM Agents
Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for …
Trustworthy, Explainable, and Sustainable Decentralized Intelligence for 6G Networks
CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation…
LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Fi…
Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
SpliTEE: Improving LLM Inference on Trusted Hardware with Differentially Private GPU Outs…
Beyond Numerical Time Series: A Unified Benchmark for Multimodal Forecasting with Heterog…
Attention Is All You Need (to Avoid Spurious Oscillations)
AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference
Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Perso…
MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup
EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse
TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language Models
Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Tempor…
Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Age…
Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured R…
Turkish MMLU Pro: Traceable Option Augmentation and Its Validity Limits in Turkish Multip…
On the role of the tokenizer in ECG transformer models
Interpreting hierarchical organisation of speaker embeddings
Don't Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatica…
Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized …
Beyond AI Literacy: A Structured Review and Exploratory Meta-Analysis of Measures for Com…
Predictive Likelihood Ratios for Language Model Watermark Detection
Kaininja: Extending Native 3D Generators to the Part Level
Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vi…
Bench2Dex: Benchmarking Visuo-Tactile Bimanual Dexterous Manipulation Across Dexterous Ha…
Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM Compression
Hidden APIs in Language Models: Discovering Reusable Causal Interfaces from Forked Futures