15
From Hugging Face to Amazon SageMaker Studio in one click
Hugging Face has launched a one-click integration with Amazon SageMaker Studio to streamline the deployment and training of machine learning models.
15
Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions
Researchers have developed CodeTracer, a forensic framework designed to detect and trace malicious backdoor attacks in large language model code completion systems.
15
3100 Opinions on Code Review in an AI World: Building Causal Theory from Practitioner Discourse
This study analyzes practitioner perspectives to build a causal theory regarding how AI coding agents affect the process and outcomes of code reviews.
15
Shift & Drift: A Zero-Shot Benchmark for Generalizable and Robust Autonomous Driving Motion Planning
Researchers have introduced Shift & Drift, a new benchmark designed to evaluate the robustness and generalization of autonomous driving motion planners under distribution shifts.
15
Using AI-based Learning Assistants in Higher Education: A Large-Scale Descriptive Analysis
A large-scale study analyzes the usage patterns of an AI-based learning assistant among over 77,000 higher education students in distance learning programs.
15
Training and Evaluating Diffusion Policies with Long Context Lengths
The study benchmarks the performance of robotic diffusion policies as their observation context length is increased, addressing memory limitations in dexterous manipulation.
15
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
A new evaluation suite called Blind-Spots-Bench has been developed to identify simple tasks that humans easily perform but multimodal AI models struggle to complete.
15
AutoPersonas: A Multi-Timescale Loop Engine for Open-Ended Persona Evolution
The AutoPersonas framework addresses the issue of behavioral collapse in long-term persona agents by enabling open-ended evolution across multiple timescales.
15
Diffusion-GR2: Diffusion Generative Reasoning Re-ranker
The authors present Diffusion-GR2, a generative reasoning re-ranker that utilizes block-diffusion language models to accelerate inference speeds in recommendation systems.
15
Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin
Researchers developed CatDT, a self-evolving multi-agent digital twin system designed to autonomously simulate and discover heterogeneous catalysts.
15
MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer
MasFACT is a continual learning framework designed to optimize and adapt communication topologies among multi-agent systems across evolving tasks.
15
Concretized Proposition Prompting Resolves Composition-Knowledge Dichotomy in Large Language Models
A prompting framework called Concretized Proposition Prompting has been developed to improve reasoning and knowledge retrieval in large language models, particularly for medical tasks.
15
Human-like Object Grouping in Self-supervised Vision Transformers
A new behavioral benchmark evaluates how closely the emergent object segmentation properties of self-supervised vision transformers align with human visual perception.
15
An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation
This paper introduces an online, reference-free evaluation framework to monitor the quality of flowchart image-to-code generation by vision-language models during inference.
15
MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation
The MultiFair framework addresses modality bias and demographic unfairness in multimodal medical classification models using dual-level gradient modulation.
15
InvestPhilBench: A Multi-Layer Benchmark for Evaluating Large Language Model Procedural Reasoning in Expert Investment Philosophy
Researchers have introduced InvestPhilBench, a multi-layer benchmark designed to evaluate how well large language models can reconstruct and apply expert investment decision frameworks.
15
Track2Map: Online Deformable SLAM with Motion-Aware Pose Optimization in Robotic Surgery
Track2Map is a new real-time 3D Gaussian Splatting system designed to reconstruct deformable anatomy during robotic surgery without relying on precise camera trajectory priors.
15
LEEVLA: Seeing What Matters in Latent Environment Evolution for Vision-Language-Action
The proposed LEEVLA architecture improves vision-language-action models for robotics by focusing on critical environmental changes rather than treating all visual data equally.
15
Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization
This survey paper categorizes and reviews recent system-level optimizations for key-value caches to improve the efficiency and throughput of large language model serving.
15
Can We Trust LLM's Logic? Quantifying Uncertainty, Coherence, and Robustness via a Graph-Based Framework
A new graph-based framework evaluates the logical consistency and uncertainty of large language model reasoning steps rather than just checking the final output.
15
Validity of LLMs as data annotators: AMALIA on authority
A study evaluates the validity of Portugal's AMALIA language model when used as an automated data annotator for identifying moral authority.
15
Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning
This paper explores optimal teaching strategies for inverse reinforcement learning to help autonomous agents learn robust reward functions across multiple environments and modalities.
15
FSD-VLN: Fast-Slow Dual-System Modeling for Aerial Long-Horizon Vision-Language Navigation
A new dual-system framework called FSD-VLN improves aerial vision-language navigation by separating high-level semantic reasoning from low-latency flight control.
15
万勋科技发布“柔韧充”自动充电通用服务引擎，以“0.000s无极容差应变”首创混沌服务、全类通解！
Wanyun Technology has launched an automated charging service engine designed to handle complex, real-world charging scenarios across public and private sectors.