Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers have developed MedExpMem, an experience memory framework that enables medical vision-language models to accumulate differential diagnosis expertise from their own diagnostic failures. The system, which mirror…
Researchers have developed a reproducible NLP pipeline for Katharevousa Greek, a historical language variant used in Greek parliamentary archives, by creating a Universal Dependencies-style parsing resource from 1,697 se…
Researchers introduced ImProver 2, a neurosymbolic framework for automated proof optimization in Lean 4 that combines a data-efficient expert-iteration pipeline with a scaffold exposing formal structure and lightweight i…
Researchers have introduced BOHM, a zero-cost attribution method for compound AI systems that extracts hierarchical attribution trees directly from existing routing weights. The method provides multi-resolution attributi…
Researchers have developed Multi-Agent Residual In-Context Learning (MARICL), a framework that uses large language model agents to analyze where a base statistical model fails and generate explicit correction terms from …
Researchers have introduced VideoOdyssey, a benchmark designed to evaluate ultra-long-context and omni-modal video understanding in AI models. The benchmark features videos averaging 109 minutes across 11 domains, requir…
Researchers have developed IaMSB, an inconsistency-aware multimodal Schrödinger Bridge framework that improves deepfake localization by jointly estimating cross-modal consistency and performing interval-level temporal ev…
Researchers have developed Query-Adaptive Semantic Chunking (QASC), a method that integrates user queries into the document segmentation process for Retrieval-Augmented Generation systems. In tests on 100 technical docum…
A new study published on arXiv demonstrates that model collapse in large language models (LLMs) — the progressive degradation of models trained on their own outputs — follows predictable patterns of cultural evolution. R…
Researchers have developed CoMoGen, a controllable video generation framework that creates realistic motion dynamics and interactions from a single binary mask sequence and an input image. The system uses a lightweight M…
Researchers introduced HawkesLLM, a framework that models how uncertainty propagates through sequential text generation in agentic simulation systems. The framework uses a multivariate Hawkes process to track temporal in…
A new computational study provides causal evidence that large language models acquire knowledge of unacceptable grammatical constructions through statistical preemption, a mechanism previously theorized in Construction G…
Researchers have developed CoReVAD, a training-free video anomaly detection framework that uses a single frozen Vision-Language Model to generate both anomaly scores and temporal descriptions without additional training …
A team of researchers improved a DETR-based fusion transformer for the MaCVi 2026 Vision-to-Chart data association challenge by adding a dedicated MLP, QueryMLP, to explicitly predict a buoy's waterline contact point in …
Researchers developed a graph neural network that models alignment topology between reference documents and LLM outputs to detect hallucinations, achieving state-of-the-art results on four datasets. The method outperform…
Researchers introduced Reflection-Augmented Scaling (RAS), a method that uses execution error messages from databases to improve Cypher query generation through in-context learning. Testing across three Neo4j datasets an…
Researchers at the German Cancer Research Center (DKFZ) developed a new "Verified Tracking" paradigm for tumor lesion tracking across serial CT scans, achieving first place in the MICCAI autoPET IV challenge. The method …
Researchers introduced PathCal, a training-free decoding controller that calibrates reasoning paths in large language models by distinguishing distinct types of reflection markers such as "wait" and "but." The system int…
Researchers have introduced EVE-Agent, a self-evolving search agent that requires each training example to include a source-grounded evidence span verifying its answer. The system uses a proposer-solver framework where a…
Researchers have developed WeCon, a weight-conditioned neural solver that achieves comparable solution quality to state-of-the-art methods while reducing inference time by 40% across multiple multi-objective combinatoria…