News

Researchers introduced CT-HEG, a bidirectional, timestamp-attributed event graph for ICU in-hospital mortality prediction, and their CHIRP-Net model achieved a 5-seed mean AUROC of 0.8449±0.0071 on MIMIC-IV v3.1 (31,142 …

Researchers introduced OncoTriad-QA, a patient-level radiology-pathology-genomics benchmark for pan-cancer question answering, containing 86.1k semantic questions across 9,281 TCGA patient cases from 32 cancer cohorts. T…

Researchers propose GLOBE (Gradient Local-Balanced Extraction), a trajectory-aligned coreset selection framework that formulates sample selection as a globally optimized sparse weighting problem, using gradient trajector…

Researchers introduced Neural Networks with Local Converging Inputs (NNLCI), a method that uses a neural network to correct numerical solutions for pricing multi-asset options, reducing root-mean-square error by a factor…

A new arXiv paper introduces 'evaluation blindness,' a condition where AI measurement functions produce healthy readings while systems fail silently, and finds that 53% of 50 verifiable public AI failures were silent. Th…

Researchers propose PAMT, a process-aligned reinforcement learning framework for multi-domain machine translation, which improves translation quality by using step-level process rewards to identify helpful intermediate t…

Researchers introduced OptR, an output-aware rotation method for INT2 KV-cache quantization that minimizes post-W_O attention-output error, improving long-context LLM inference efficiency. Across three models and five re…

Researchers propose NANQ, a noise-aware mixed-precision non-uniform quantization framework for analog compute-in-memory (CIM), which models magnitude-dependent weight noise from measured eFlash CIM arrays to assign finer…

Researchers introduced FLARE (Few-shot Learning-based Adaptive Reflective Engine), a framework that uses reflective mechanisms and few-shot reference examples to optimize prompts for large language models, outperforming …

Researchers introduced Local Credit Assignment (LoCA), a two-stage method for parameter-efficient fine-tuning of large language models that requires only one backward pass for calibration, after which tuning proceeds for…

Researchers propose OPTD (On-Policy Transition Distillation), a method that improves few-step diffusion language models by sampling from the student's own trajectories and using a frozen teacher to adaptively compress st…

A new arXiv preprint (2608.03035v1) shows that large language models (LLMs) encode contextual truth—propositions whose truth depends on in-context evidence—along linear directions in activation space, persisting across d…

An AI-powered knowledge graph platform that maps SQL errors to conceptual gaps in database courses achieved 95.7% validity for extracted nodes and 63.8% fully correct triplets in an expert study, according to a paper rel…

A new arXiv preprint (2608.02830v1) reveals that many-shot in-context learning can cause a sharp accuracy drop, termed 'in-context collapse,' in vision-language models (VLMs), with some models falling below chance while …

Researchers propose a human-in-the-loop deep learning framework for color reconstruction of historical lenticular films, addressing failures of automated methods on curved lenticules, low-contrast, or badly captured regi…

Alibaba Group's Qwen team introduced Qwen-3D, a geometry-aware large multimodal model that compresses visual information using multi-view geometric cues and 3D Rotary Positional Embeddings, enabling efficient long-horizo…

Researchers propose Meta-Persona Anchoring with Filtered Temperature Scaling (FTS) to reduce the 'Artificial Hivemind' effect in large language models, cutting average pairwise cosine similarity from approximately 0.85 t…

Researchers propose Urban-Agent, a tool-augmented agent framework that combines a large language model with code execution, API calls, and Model Context Protocol to handle cross-system urban tasks. In evaluations using t…

A systematic review of 2,643 records found that only 19 of 57 full texts substantively integrate both legal and technical perspectives on Explainable AI (XAI) and the EU Right to Explanation, revealing a significant gap …

A new paper on arXiv (2608.02704v1) introduces Predictive Set Theory (PST), a formal generative framework that reconstructs cognitive architecture from first principles, anchoring cognition in a minimal set of operations…