Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced Frost Training, a method that improves Monte Carlo-based policy optimization for Cross-Entropy Games by exploiting the gradient of the reward function in embedding space. The technique, validated u…
Researchers have developed a hierarchical control-and-learning framework for large language models deployed in resource-constrained agentic systems, addressing failures caused by prompt extension beyond a model's effecti…
Researchers introduced Sequential Bayesian Belief Tracking (SBBT), a framework that estimates the likelihood of a correct final answer from partial reasoning traces by calibrating observation likelihoods and updating a t…
Researchers have developed techniques to enable fine-grained and within-utterance speaking style control in prompt-based text-to-speech models. The methods allow smooth style interpolation between utterances and time-var…
Researchers have developed RAG-Coding, a method that uses four large language model agents to automate ICD-10-CM medical coding by grounding decisions in official coding tabular lists and guidelines. On the MDACE dataset…
Researchers at the University of Cambridge have identified a fundamental trade-off between stability and expressivity in spoken language models trained on synthetic data, where phonetic accuracy improves but prosodic var…
Researchers have developed EvoSpec, a framework that enables real-time evolution of draft models in speculative decoding through dynamic vocabulary and parameter adaptation. The system addresses the failure of static pru…
A new study published on arXiv reveals that language models consistently learn to verify factual knowledge before they can generate it, creating a "generation-verification gap" that persists across training phases. Resea…
NVIDIA's CUTLASS library, a header-only C++ template framework for writing custom CUDA kernels, powers much of the AI infrastructure behind FlashAttention, vLLM, and PyTorch's internal kernels. The library enables develo…
Pony.ai launched PonyWorld 2.0, an upgraded proprietary world model and training system for its L4 autonomous driving technology, on April 10. The system adds self-diagnosis, targeted data collection, and more efficient …
A new study from researchers testing six large language models across four capability tiers found that the relationship between model capability and optimal harness complexity is non-monotone, contradicting the assumptio…
A developer exploring sparse embeddings for retrieval-augmented generation (RAG) detailed the progression from term frequency (TF) to inverse document frequency (IDF) and TF-IDF, culminating in the BM-25 algorithm. The e…
A developer successfully quantized Google's Gemma 4 model to 4-bit precision using llama.cpp on a Mac with Metal acceleration. The process involved converting the model to GGUF format and applying the Q4_K_M quantization…
DTensor, PyTorch's distributed tensor abstraction, attaches placement metadata to every tensor to automatically propagate layouts and insert correct collective operations during distributed training. While this approach …
A machine learning analysis of 38,018 UK Biobank participants has revealed that childhood trauma amplifies genetic risks for depression in ways conventional statistical methods have missed. Yale University researchers us…
A compiler engineer at SemiAnalysis spent over $10,000 in a single afternoon running AI agents to fuzz NVIDIA's closed-source ptxas compiler, uncovering approximately 80 miscompilation bugs in three days. The researcher,…
Researchers from Sakana AI and the University of Tokyo developed DiffusionBlocks, a block-wise training framework that converts residual networks into independently trainable denoising modules. The method partitions a ne…
A team of compliance engineers spent six months feeding their specialist screening data, edge cases, and analyst feedback into a major cloud AI platform, only to discover they were training a general-purpose model with t…
Researchers argue that AI agent security must be treated as a systems-level problem, with the AI model itself considered an untrusted component and security invariants enforced at the system level rather than through mod…
AMD's ROCm platform now supports PyTorch, Ollama, LM Studio, and ComfyUI out of the box, enabling local AI workloads on AMD GPUs without the compatibility issues that plagued earlier versions. Users with a 32GB Radeon GP…