Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learn…
Explorar
Noticias de IA
22116 elementos — filtrados, clasificados y sin duplicados
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing
Claude Fable 5's Hardest Test Was Knowing the Metric Was Wrong
Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning
Finding Multiple Interpretations in Datasets
Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion La…
How memory tools can make AI models worse
German court holds Google liable for false AI Overview answers
VIA-SD: Verification via Intra-Model Routing for Speculative Decoding
Re-evaluating Confidence Remasking in Masked Diffusion Language Models
Making Foresight Actionable: Repurposing Representation Alignment in World Action Models
MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representatio…
A Resource for Enthymeme Detection in Controversial Political Discourse
How Low Can You Go? Active Learning for Sparse Model Discovery in the Ultra-Low-Data Limit
Time-Conditioned and Multi-Time Survival Prediction from 2D PET/CT Projections in Lung Ca…
Q-Fold: Query-Aware Focus-Context Spatio-Temporal Folding for Long Video Understanding
Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Langu…
MSUE: Multi-Modal Soccer Understanding Expert
DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model
Automating Geometry-Intensive Compliance Checking in BIM: Graph-Based Semantic Reasoning …
Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident Understanding
MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning
Waymo made a virtual human driver to improve its robotaxis
Exploration Structure in LLM Agents for Multi-File Change Localization
Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Data
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills
The worlds first AI-designed vaccine, explained
Conformal Bayes under Label Shift: Post-Hoc Calibration vs. In-Training Adaptation