Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced HyPOLE, a framework for multi-agent reinforcement learning under partial observation that uses hyperproperty specifications in HyperLTL to guide policy synthesis. The framework integrates centraliz…
Researchers introduced AgRefactor, an LLM-based multi-agent workflow that refactors software into HLS-compatible code with a self-evolving memory system. On 9 of 11 challenging benchmarks, it outperformed state-of-the-ar…
Researchers argue that AI agents should help users construct preferences rather than assume they have well-formed ones, introducing CoPref and CoShop to model and benchmark this. Testing five frontier models on CoShop, n…
Researchers introduced BayesBench, a suite of simulation environments to evaluate how large language models update beliefs under multi-turn evidence accumulation. Testing seven LLMs from 3B to 70B parameters, they found …
Researchers introduced a Bangla event detection benchmark with 9,979 annotated sentences across clean text, ASR transcripts, and corrupted text. They found encoder models perform better on clean text but degrade under no…
KAIST researchers developed BehaVERT, an AI model that interprets mouse gestures by converting skeletal movements into language-like tokens, outperforming previous systems on five international benchmarks. Published in t…
A study of 15,676 HELIUS participants found that combined assessment of LDL-C, Lp(a) and hsCRP identifies individuals at greater long-term risk of atherosclerotic cardiovascular disease (ASCVD), with those having all thr…
A developer built Kognita, a managed API that handles chunking, embedding, indexing, and retrieval for AI knowledge layers. The project is seeking 10 teams to test the service for free, with no credit card required and h…
Google researchers have found that scaling laws similar to those for large language models apply to wearable sensor data, with validation loss scaling predictably with compute, model size, and data size. The scaling law …
Researchers introduced Symbolic Mechanistic Data Attribution (SMDA), a framework that links training data to high-level model behaviors, tested on Llama-3.2-3B-Instruct. SMDA revealed systematic safety gaps and biases, o…
GitHub trending repos this week show a shift from building new things to optimizing existing processes, with AI-driven efficiency and visual processing capabilities leading the charge. Ponytail, an ecosystem for extreme …
Scientists used machine learning to analyze seismic data and discovered a razor-sharp line of thousands of previously undetected earthquakes beneath Alaska, revealing the precise edge of the subducting Yakutat microplate…
A developer identified two necessary conditions for FalkorDB's db.idx.vector.queryNodes to work properly: data must be stored as a vector type using vecf32() and a vector index must be created. Common pitfalls include st…
Researchers have found that continuous reward models in reinforcement learning are oversensitive, assigning different scores to equally good responses, which can lead to bad policies. They propose evaluating reward model…
Shanghai AI Laboratory's Agents-A1, a 35-billion-parameter Mixture-of-Experts model, matches or outperforms trillion-parameter rivals by training on longer task sequences instead of increasing parameter count. Released u…
A developer designed a scalable audio transcription pipeline using Faster-Whisper, a highly optimized implementation of OpenAI's Whisper model. The pipeline focuses on high-throughput GPU inference, batch processing, and…
A developer outlines a production-ready RAG pipeline that combines dense vector search with BM25 keyword search via Reciprocal Rank Fusion, adds a cross-encoder reranker for accuracy, and emphasizes rigorous evaluation w…
A blog post by John D. Cook connects central Delannoy numbers, which count king moves on a chessboard, to DNA sequence alignment. The Delannoy numbers D(m,n) represent the number of possible alignments between two DNA st…
AI agents are beginning to search, compare, recommend, negotiate, and complete transactions on behalf of users, creating a new paradigm called agentic commerce. This shift requires common protocols for intent, identity, …
A developer details practical QLoRA fine-tuning using Axolotl and Unsloth, explaining how parameter-efficient methods like LoRA and QLoRA enable training multi-billion parameter models on a single consumer GPU. The post …