Researchers introduced RoMaP, a 3D Gaussian editing framework that enables precise local edits through innovative mask generation and loss techniques. The framework achieves state-of-the-art performan…
Quantization of large language models reduces accuracy loss but increases reasoning chain length, inflating token usage and compute costs. Researchers introduced the CoT Token Inflation Ratio to measu…
Researchers have introduced diffusion crossover, a method that redefines evolutionary recombination within Denoising Diffusion Probabilistic Models (DDPMs) for generating semantically rich images. By …
Researchers have developed novel methods to combat data corruption in offline reinforcement learning with human feedback (RLHF), integrating corruption-robust techniques to derive reliable policies fr…
Researchers introduced Histogram-constrained Image Generation (HIG), a new method for diffusion models that uses optimal transport theory to enforce user-specified distributional constraints like colo…
Cohere and LG CNS have unveiled LuckyStar 111B, a hybrid reasoning model designed to enhance AI agility for Korean-English enterprise tasks. Built on Cohere's Command A model, it uses multilingual fin…
Researchers introduced ADAPT, a framework that reduces hallucinations in multimodal large language models by up to 60% through refining text-to-image cross-attention dynamics. The approach uses a cros…
A new study reveals that AI models often exhibit 'performative compliance', appearing fair only when explicit demographic labels are provided. When such labels are removed, harmful decisions increase …
BiRG-LoRA, a single-adapter rank-gated method, achieves 69.31% macro-average accuracy on medical QA benchmarks while using 28.1% fewer parameters than MoELoRA, offering a more efficient and accurate A…
Researchers introduced BlockPilot, a new speculative decoding method that adapts block sizes to individual inputs, achieving up to 4.20 times speedup on Qwen3-4B. The approach reduces document process…
Researchers introduced Outcome Reward Models (ORMs) for Text-to-SQL verification, using semantic scoring to outperform traditional heuristics. Their GradeSQL framework automates candidate generation a…
ELEVATE introduces a local-first AI tutoring framework using 3D avatars and LLMs, deployed on standard consumer hardware to address privacy and access issues in education. The prototype succeeded in r…
Intraoperative AI tools are set to revolutionize surgical care by offering real-time insights and quality assessment, promising significant improvements in patient outcomes. The technology uses endosc…
A new study reveals that large language models with higher self-consistency are more prone to errors, particularly in critical fields like healthcare. The research tested ten models across 491 concept…
AxDafny, a verifier-guided framework, achieved a 92.7% verification success rate on DafnyBench, outperforming GPT-5.5 by 6.5 percentage points. The tool generates code with proof artifacts, setting a …
AI-driven materials discovery is advancing with new techniques that reduce costs and improve efficiency. Researchers have integrated a Gaussian process acquisition gate into the workflow, allowing mod…
Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory has deployed an AI framework that reduces plant image analysis from weeks to seconds, using a conversational Co-Scientist Agent an…
Large language models are powering an adaptive vehicle routing system that dynamically clusters and refines routes for large-scale logistics, handling up to 500,000 customers. The approach outperforms…
Tech firms that replaced human workers with AI are now rehiring them after realizing AI's limitations. Companies like XYZ Corp and ABC Inc saw customer satisfaction plummet after switching to chatbots…
Researchers introduced ReMatch, a method that uses optimal transport in PCA space to align training and test-time residual distributions, reducing under-dispersion in probabilistic downscaling. In tes…