HuggingFace
Agentic discovery of blood biomarker from distilled private health records
Routine complete blood counts (CBCs) could yield new biomarkers, but the private records needed to evaluate candidate...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
The Numerical Linear Algebra of Large Language Models
Numerical Linear Algebra (NLA) has consistently played a vital role in advancing science by providing tools to solve ...
HuggingFace
When Does Selection Replace Extraction? A Pre-Registered Test of Agent Memory with a Typed Decision Model
Does conversational memory need LLM-extracted facts, or is selecting the right raw turns enough? Published results di...
arXiv
Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification
The unprecedented computational scale of modern artificial intelligence depends on complex, multi-billion-transistor ...
arXiv
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation ...
arXiv
Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution
A language model can give a correct answer more probability than any single incorrect answer and still usually sample...
arXiv
TAPDreamer: Transferable Adversarial Patches for World Action Models
World models learn to predict how their environment will evolve, making them an important foundation for general-purp...
arXiv
Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model
We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model...
arXiv
Deep Learning for Sleep Heart Rate Estimation from Accelerometers: Toward Population-Scale Cardiac Insight Without Optical Sensors
Large longitudinal cohorts often contain wrist accelerometry without optical heart-rate sensing, motivating recovery ...
arXiv
TasteVal: Measuring the Experimental Research Taste of AI Systems Against Human Experts
We introduce TasteVal, a benchmark to evaluate the experimental research taste of frontier models. We define research...
arXiv
CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling
Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement...
arXiv
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents
Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions...