News
AI, cybersecurity, machine learning, scraping & programming news.
21 results on this page · clear filters
Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data
When Running Out of Data Breaks Sparse Models The internet's text is finite. As language model training scales toward and beyond the limits of human-written corpora, repeating data has become standard practice. Muennighoff et al....
Distance generalization in transformers: why bother with positional encoding?
Positional Encoding May Be Hurting Your Transformer Transformers are everywhere, and positional encoding is considered foundational. Every major production model, from Llama to DeepSeek, uses RoPE (Rotary Position Embeddings) to t...
TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription
Automatic Music Transcription for guitar has long been stuck on the wrong side of the difficulty curve compared to piano. Piano AMT hit high note-level accuracy years ago through CRNN models and large paired datasets, but guitar t...
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Modern AI systems can write code, reason through graduate-level science, and plan multi-step research workflows. But every improvement they undergo still requires humans to decide what to fix, build the resources to fix it, and ju...
Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
Diffusion models and flow-matching models generate images by progressively denoising a noisy sample over a series of timesteps. How that time is allocated across the denoising process, the schedule, has a direct impact on sample q...
Generative Late-Interaction Embeddings For Visual Document Retrieval
Late-interaction retrieval has become the dominant paradigm for searching visual documents. Models like ColPali embed every image patch on a page as a separate vector and score queries against them using MaxSim, a per-token maximu...
Thinking with Looped Flows
The ability to solve harder problems by spending more time on computation is one of the most fundamental ideas in both human cognition and computer science. Autoregressive language models achieve this by writing out their reasonin...
Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics Generalization
World models are supposed to learn dynamics, not just predict the next frame. But does a model that predicts the next latent state accurately over a single step actually understand physics when that prediction is composed over doz...
Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation
How Amazon Trains a 15M-Parameter Model to Replace LLM Calls for Product Upgrade Recommendations E-commerce platforms need to recommend better products to customers, not just similar ones. A shopper buying a basic moisturizer shou...
Revise is the Figma of machine learning
Machine learning workflows are slow, fragmented, and often require sending sensitive data to cloud services. Revise, a new no-code platform, tries to solve all three problems at once by providing a guided interface for cleaning da...