Discovering Millions of Interpretable Features with Sparse Autoencoders
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
LAMP: Lane-Aligned Motion Primitives for Feasible Trajectory Prediction
Zero-Shot Size Transfer for Neural ODEs on Sparse Random Graphs: Graphon Limits and Adjoi…
Learning Motion Feasibility from Point Clouds in Cluttered Environments
Robust Onion: Peeling Open Vocab Object Detectors Under Noise
AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing
Efficient foundation decoders for fault-tolerant quantum computing
Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks
Automating Potential-based Reward Shaping with Vision Language Model Guidance
GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning
Scaling Multi-Reference Image Generation with Dynamic Reward Optimization
[AINews] OpenAI reports median internal Codex output tokens grew 56x in Research, 32x in …
Training Observable Control Policies to Expose Agent State Through Actions
Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Fea…
Autoregressive Boltzmann Generators
Retrofit, don’t rebuild: Agentic overlays for transforming legacy enterprise services
Hallucination in World Models is Predictable and Preventable
Multilingual Reasoning Cascades Need More Context
Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN
A Multi-Fidelity Convolutional Autoencoder-Transfer Learning Framework for Guided-Wave-Ba…
Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semant…
Recovering Governing Equations from Solution Data: Identifiability Bounds for Linear and …
How Good Can Linear Models Be for Time-Series Forecasting?
E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
Databricks’ former AI chief thinks he can cut AI’s power bill by 1,000x
CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs
Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy
Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement
SatSplatDiff: Geometry-preserving generative refinement for high-fidelity satellite Gauss…
Which tokens does a hybrid model predict better?