AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchGraded-Relevance Composed Multimodal Retrieval for E-commerce Visual Search at Scale
arXiv:2609.24152v1 Announce Type: cross Abstract: Visual search on large e-commerce catalogs must serve both "similarity" queries that ask for items resembling an uploaded image and "modifier" queries that comprise an im…
- arXiv cs.AIresearchTAC-Time: Texts as Channels For Multimodal Time Series Forecasting
arXiv:2609.24156v1 Announce Type: cross Abstract: Most existing time series forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts. Recent multimodal appro…
- arXiv cs.AIresearchOpinion Leader Dynamics: How Sparse Attention Shapes Token Clustering
arXiv:2609.24202v1 Announce Type: cross Abstract: Sparse attention reduces the quadratic cost of global self-attention while retaining strong empirical performance, but how its restricted interactions shape the evolution…
- arXiv cs.AIresearchMemory vs. Context? Influential Factors of Factual Recall in Language Models
arXiv:2609.24238v1 Announce Type: cross Abstract: We reproduce and stress-test the work of Yu et al. (2023), who characterize how language models (LMs) arbitrate between memorized knowledge and contradictory in-context s…
- arXiv cs.AIresearchHessian Rank Constraint for Learning Structure of Nonlinear Latent Variable Models
arXiv:2609.24241v1 Announce Type: cross Abstract: Uncovering latent variables and their causal relations from observed data is a fundamental yet challenging problem. Existing methods often rely on restrictive assumptions…
- arXiv cs.AIresearchTaramandal-GPT: Enhancing Astrodynamics Problem-Solving with Knowledge Retrieval and Structured Thinking
arXiv:2609.24246v1 Announce Type: cross Abstract: Large language models (LLMs) have shown remarkable progress in natural language understanding, yet their effectiveness in specialized fields like astronomy and astrodynam…
- arXiv cs.AIresearchvla.simd: Efficient CPU Inference for Language-Conditioned Manipulation
arXiv:2609.24274v1 Announce Type: cross Abstract: Deploying language-conditioned manipulation without a dedicated GPU requires efficient inference and action chunks that cover the delay between policy queries. We present…
- arXiv cs.AIresearchTemporal Generalization and Explanation Stability of Control Flow Graph Neural Networks for Malware Detection
arXiv:2609.24280v1 Announce Type: cross Abstract: Malware detection is a critical task in cybersecurity, and graph neural networks over control flow graphs have shown promising results for it. However, detectors are usua…
- arXiv cs.AIresearchKV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation
arXiv:2609.24298v1 Announce Type: cross Abstract: What limits KV-cache compression at extreme bit-rates? We argue that it is not the choice of compression scheme, but how its budget is allocated across attention heads. E…
- arXiv cs.AIresearchAdapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening
arXiv:2609.24302v1 Announce Type: cross Abstract: Virtual screening aims to prioritize active compounds from large chemical libraries within a limited experimental budget. When applying Boltz-2 to virtual screening, a ke…
- arXiv cs.AIresearchThe Undetected Damage of Quantization on Retrieval and How to Fix It
arXiv:2609.24322v2 Announce Type: replace-cross Abstract: We show that a quantized model that keeps its classification accuracy still changes $14$ to $46\%$ of its top-1 retrieval results, and that aggregate ranking metr…
- arXiv cs.AIresearchMitigating Entity Type Confusion in Cross-Domain NER via Multidimensional Quantification and Reasoning Enhancement
arXiv:2609.24357v1 Announce Type: cross Abstract: Cross-domain Named Entity Recognition (CD-NER) aims to transfer the rich knowledge in the source domain to the target domain. Recent studies adopting decomposition or gen…
- arXiv cs.AIresearchDeceptionAnalyser: A Web-Based AI Tool for Performing Structured Deception Analysis with Argumentation Schemes and LLMs
arXiv:2609.24369v1 Announce Type: cross Abstract: Deception plays a central role in Intelligence operations, yet it remains difficult to analyse systematically without expert knowledge of reasoning patterns and cognitive…
- arXiv cs.AIresearchURA-NER: A Unified Retrieval-Augmented Framework with Retrieval Alignment and Uncertainty Reduction for Low-Resource NER
arXiv:2609.24372v1 Announce Type: cross Abstract: In-context learning (ICL) based on large language models (LLMs) has shown promising potential in alleviating performance bottlenecks caused by the limited availability of…
- arXiv cs.AIresearchInformation-Time Proximal Policy Optimization
arXiv:2609.24380v1 Announce Type: cross Abstract: RLVR has substantially improved the reasoning capabilities of LLMs. However, existing methods typically parameterize temporal progression in the Markov Decision Process b…
- arXiv cs.AIresearchTactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors
arXiv:2609.24385v1 Announce Type: cross Abstract: Tactile sensing is an essential modality for robots performing contact-rich, dexterous manipulation, particularly under visual occlusion. While pre-trained image encoders…
- arXiv cs.AIresearchArtificial Structure Function Search: Preserving Artificial Functional Connectivity for Structured Pruning
arXiv:2609.24401v1 Announce Type: cross Abstract: Structured pruning is a model compression technique that is used to reduce the computational cost of deploying deep neural networks on resource-constrained devices. Popul…
- arXiv cs.AIresearchARM: Attention with Routed-Memory for Learnable Sparse Control
arXiv:2609.24417v1 Announce Type: cross Abstract: Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are necessary for stab…
- arXiv cs.AIresearchEstimating Accurate Hand Pose in Camera Space with Vision Transformer
arXiv:2609.24424v2 Announce Type: replace-cross Abstract: Monocular RGB-based hand pose estimation has emerged as a critical research frontier in computer vision. The local hand pose estimation methods predict hand poses…
- arXiv cs.AIresearchFoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding
arXiv:2609.24433v1 Announce Type: cross Abstract: Low-bit vision-language-action inference must reduce observation-to-action latency while preserving robot behavior. We present FoldQuantVLA, a post-training quantization…
- arXiv cs.AIresearchWPBench: A Comprehensive Benchmark for Wind Power Forecasting
arXiv:2609.24444v1 Announce Type: cross Abstract: Accurate, reliable, and deployable wind power forecasting is critical for power system dispatch, renewable energy integration, and electricity market operations. Progress…
- arXiv cs.AIresearchDo LiDAR Language Models Really Understand Spatio-temporal Relationships?
arXiv:2609.24452v1 Announce Type: cross Abstract: Recent 4D LiDAR language models aim to reason about objects and their evolving spatial relationships. Yet, in our evaluation, always selecting the same option nearly matc…
- arXiv cs.AIresearchConduit: An Experience Data Plane for Distributed Reinforcement Learning
arXiv:2609.24456v1 Announce Type: cross Abstract: Distributed reinforcement learning (RL) scales training by parallelizing actors and learners around an Experience Buffer. As RL workloads grow, however, the buffer become…
- arXiv cs.AIresearchVPRune: Efficient Training-free Pre-LLM Visual Token Pruning
arXiv:2609.24485v2 Announce Type: replace-cross Abstract: Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction often causes s…
- arXiv cs.AIresearchLifted Bellman Linear Programming for Offline Reinforcement Learning
arXiv:2609.24489v2 Announce Type: replace-cross Abstract: Offline reinforcement learning (RL) typically trains a critic by minimizing a regression loss against bootstrapped value targets stabilized by target networks wit…
- arXiv cs.AIresearchOn Emergent Capabilities and Model Merging
arXiv:2609.24504v2 Announce Type: replace-cross Abstract: Fine-tuned checkpoints and adapters now fill public repositories, and the most common operation applied to these artifacts is model merging: arithmetic on their w…
- arXiv cs.AIresearchQLoRA Fine-Tuning of Ministral LLM for Sequence-to-Function Protein Annotation
arXiv:2609.24538v1 Announce Type: cross Abstract: Functional annotation of newly sequenced proteins remains a bottleneck in molecular biology: the number of sequences in public repositories grows far faster than the capa…
- arXiv cs.AIresearch$t_0$: A Time-Series Foundation Model for Forecasting with Context
arXiv:2609.24559v1 Announce Type: cross Abstract: We present $t_0$, a family of open-weights foundation models for forecasting with multivariate context. We release its first two members: $\texttt{t0-alpha}$ and $\texttt…
- arXiv cs.AIresearchOverlay\_dx - Automating forecasting evaluation
arXiv:2609.24586v1 Announce Type: cross Abstract: Traditional evaluation metrics provides numerical values but often lack comprehensibility, hindering effective differentiation of model performances. Our work addresses t…
- arXiv cs.AIresearchGraphToolbox: A Configurable Python Framework for Graph Neural Network Forecasting
arXiv:2609.24609v1 Announce Type: cross Abstract: Electricity forecasting often involves spatially related signals observed over regions, substations, and feeders, and Graph Neural Networks (GNNs) provide a natural way t…
- arXiv cs.AIresearchFedMust: Semi-supervised Multi-task Student-Teacher Federated Learning for Multi-organ CT Segmentation
arXiv:2609.24627v1 Announce Type: cross Abstract: Multi-organ segmentation using deep learning requires large amounts of annotated patient data; however, institutions often lack sufficiently large and diverse annotated d…
- arXiv cs.AIresearchAugmented Hypothesis Testing with Persona-Based LLM Simulations
arXiv:2609.24629v1 Announce Type: cross Abstract: A/B testing requires large sample sizes, long timelines, and significant costs. When auxiliary predictions of experimental outcomes are available from machine learning mo…
- arXiv cs.AIresearchAnnie, Are You Okay? How Style- and Context-Based Personalization Shape AI-Assisted Decision-Making
arXiv:2609.24644v1 Announce Type: cross Abstract: As people turn to generative AI for financial advice, these systems can personalize how they communicate and what they say. Whether these forms of personalization shape d…
- arXiv cs.AIresearchiSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs
arXiv:2609.24646v2 Announce Type: replace-cross Abstract: On-policy self-distillation fine-tuning (SDFT) learns new skills from demonstrations while reducing forgetting, but it always distils toward the full demonstratio…
- arXiv cs.AIresearchCorrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement
arXiv:2609.24651v1 Announce Type: cross Abstract: Diffusion and flow models, as promising generative paradigms for speech enhancement, face a training--inference mismatch: training uses analytical path states, whereas in…
- arXiv cs.AIresearchTouch2Robot: Robot Touch in the Human Demonstration Loop
arXiv:2609.24660v2 Announce Type: replace-cross Abstract: Human demonstrations offer a scalable way to collect manipulation data, but their contacts may be unstable or infeasible when transferred to a robot hand. Collect…
- arXiv cs.AIresearchUnderstanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion
arXiv:2609.24688v1 Announce Type: cross Abstract: Angular-margin speaker encoders are widely used in voice conversion, yet the geometry of their classifier prototypes remains poorly understood. We analyze ECAPA-TDNN clas…
- arXiv cs.AIresearchWhat Makes a Good Medical Image Tokenizer? Rethinking Reconstruction and Generation in Medical Image Tokenization
arXiv:2609.24691v1 Announce Type: cross Abstract: Latent diffusion models now dominate medical image generation, and every such pipeline rests on a \emph{tokenizer} that compresses images into the latent codes for image…
- arXiv cs.AIresearchAdapting Tree-Structured Speculative Decoding to DeepSeek-V4 for Efficient Inference
arXiv:2609.24698v1 Announce Type: cross Abstract: Repeated execution of the target model during autoregressive decoding is a major source of LLM inference latency. Unlike linear speculation, which follows a single candid…
- arXiv cs.AIresearch"MeBo Leaves a Piece of You Behind": Designing a Relational Voice-Based Memory Companion for Older Adults
arXiv:2609.24706v1 Announce Type: cross Abstract: Autobiographical remembering supports identity, well-being, and social connection in later life, yet voice-based memory technologies largely rely on isolated prompts. We…
- arXiv cs.AIresearchReasoning Topology Matters: A Controlled Study of LLM-Based Cybersecurity Analysis
arXiv:2609.24710v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used in cybersecurity, where accurate analysis often requires multi-step and context-dependent reasoning over complex and he…
- arXiv cs.AIresearchA digital-twin framework for forecasting treatment-day imaging with contour uncertainty in adaptive proton radiotherapy
arXiv:2609.24725v1 Announce Type: cross Abstract: Head-and-neck anatomy changes over a six-to-seven-week proton course, and the anatomy of a later week cannot be imaged when the plan is made. We present a digital-twin fr…
- arXiv cs.AIresearchEnhancing Transformer Representations of Symbolic ODE Expressions
arXiv:2609.24746v1 Announce Type: cross Abstract: Existing approaches to solving differential equations, such as symbolic regression, physics informed neural networks, and neural operators, typically focus on numerical a…
- arXiv cs.AIresearchNPU Accelerator: Quantized Real-Time Vehicle Detection on PYNQ-Z1 Using FINN
arXiv:2609.24757v1 Announce Type: cross Abstract: This paper presents the design, optimization, implementation, and on-board validation of a neural processing unit (NPU) accelerator for real-time vehicle detection on the…
- arXiv cs.AIresearchWhen Quantization Preserves Accuracy but Not Evidence: Explanation-Aware Post-Training Quantization for Medical LLMs
arXiv:2609.24799v1 Announce Type: cross Abstract: Post-training quantization (PTQ) enables efficient deployment of large language models, and PTQ methods are usually optimized and evaluated with generic reconstruction, p…
- arXiv cs.AIresearchDecoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection
arXiv:2609.24801v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in production systems, raising concerns about their exposure to adversarial manipulation through prompt injection a…
- arXiv cs.AIresearchMobile Imaging Solutions for Medical Diagnosis: Trends and Applications
arXiv:2609.24814v2 Announce Type: replace-cross Abstract: Advances in processing power, camera technologies, and mobile image analysis have made smartphones and other mobile devices, such as laptops, increasingly suitabl…
- arXiv cs.AIresearchUranus: Building the Next-Generation Simulation Infrastructure for Embodied AI
arXiv:2609.24815v3 Announce Type: replace-cross Abstract: Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional…
- arXiv cs.AIresearchSPECTRA: Adaptive Execution of Speculative Decoding on a Runtime-Reconfigurable Tiled Architecture
arXiv:2609.24847v1 Announce Type: cross Abstract: LLM inference on edge devices is constrained by computational and memory resources, making efficient autoregressive decoding challenging. Speculative decoding alleviates…
- arXiv cs.AIresearchSE(3) Neural Potential Fields for 6-DoF Trajectory Planning Directly from Images Without Explicit 3D Reconstruction
arXiv:2609.24864v1 Announce Type: cross Abstract: Reaching a 6-DoF grasp pose in clutter requires a collision-free trajectory, conventionally obtained by reconstructing the scene in 3D and planning inside that reconstruc…