Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers present AffectFlow-DINO, a multi-task learning system for the 11th ABAW challenge that uses a conditional rectified-flow head to model ambiguity in facial behavior, achieving a multi-task learning performance…
Researchers at MPI Informatics have developed a differentiable polarized path tracing method that enables stable gradient estimation for inverse rendering, overcoming numerical instability caused by rank-deficient polari…
Researchers propose Phase-Aware Knowledge Tracing (PAKT), a framework that decomposes student interactions into ability and proficiency phases to improve knowledge tracing. Experiments on six public benchmarks show PAKT …
A new Context-Augmented Prompting framework improves molecular property prediction in small language models by integrating graph-based tools, achieving up to 74% relative accuracy gains on Tox21, though a gap to speciali…
Researchers propose a decoupled transfer learning strategy that adapts normalization layers and precomputes features once, reducing training overhead without end-to-end backpropagation. Evaluated on four CNN architecture…
A systematic review of Federated Explainable Artificial Intelligence (FedXAI) finds that explainability is transitioning from a post-hoc tool to an integral component of the federated learning lifecycle, according to a n…
Cogni-ML, a Crystal machine learning library, now supports native Apple Silicon GPU acceleration with Metal inference for GGUF models, including nomic-embed-text-v2-moe embeddings and Qwen 3.5 9B text generation. The lib…
A 200-step, ~1.7B-parameter ablation run in OLMo-core comparing Engram on a standard attention Transformer versus a 3 GDN-layer + 1 attention-layer hybrid found that Transformer + Engram reached slightly lower cross-entr…
Researchers present Fleet, a hierarchical task-based abstraction for multi-die GPUs that introduces Chiplet-tasks to exploit chiplet-level locality and synchronization. On AMD Instinct MI350 with Qwen3-8B, Fleet achieves…
Researchers present a method to accelerate block low-rank inference for foundation models on memory-constrained GPUs, improving efficiency without sacrificing accuracy. The technique reduces memory bandwidth and computat…
A developer successfully ran Google's Gemma 4 E2B and E4B models on Apple's Neural Engine (ANE) using CoreML, achieving a memory footprint under 1 GB on an iPhone 17 Pro. The project overcame ANE's lack of native matrix …
Researchers have released SynapticOS, an open-source inference-first runtime for neural processing units on resource-constrained microcontrollers, built on Zephyr. The runtime achieves constant-time memory allocation (~1…
USC researchers will present three papers at the 2026 Robotics: Science and Systems (RSS) conference in Sydney, Australia, covering robotic foundation models, humanoid loco-manipulation, and robot manipulation learning. …
A developer argues that AI database agents need human review queues, not just approval buttons, to handle uncertainty in real workflows. The review queue should capture ambiguous metric definitions, missing filters, part…
LFortran and Enzyme enable exact gradients from legacy Fortran code without rewriting, turning validated physics solvers into differentiable layers for JAX. The experimental stack compiles Fortran to LLVM IR, differentia…
AMD has tagged ROCm 7.14 "TheRock" tech preview, bringing AI training enhancements, performance improvements of 10-16% for select workloads like Comfy UI, and continued Microsoft Windows support for the open-source GPU c…
Researchers from Inception3D released TTT3R, a 3D reconstruction method that treats reconstruction as test-time training, with open-source code and pre-trained checkpoints on GitHub. The method builds on CUT3R and suppor…
Fusion energy is edging closer to practical use with AI-driven advances and better plasma containment, but the pathway to commercialization remains fraught with high costs and economic challenges. Artificial intelligence…
Researchers introduced LOTUS (Looped Transformers with parallel supervision on latents), the first latent chain-of-thought method to match explicit CoT performance at the 3B parameter scale while reducing thought-phase l…
The latest update to hermes-memory-installer introduces an auto-repair mechanism for missing embeddings in the gbrain module, selectively rebuilding only affected subsets instead of triggering a full reinstall. This fix …