AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchWhat We Talk About When We Talk About LLM Planning: Evidence for Two Distinct Planning Abilities
arXiv:2607.11197v2 Announce Type: replace Abstract: When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is incomplete, as task-le…
- arXiv cs.AIresearchInstruction-Tuned Language Models Cannot Sample from Distributions They Can Describe
arXiv:2607.25292v3 Announce Type: replace Abstract: Silicon sampling uses language models as proxies for human survey respondents, treating each model call as an independent draw from the persona's response distribution.…
- arXiv cs.AIresearchLEMUR: Learning to Align with Multi-Objective Reinforcement Learning from Preference Feedback
arXiv:2607.29559v2 Announce Type: replace Abstract: Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function. However, real-world decision-making tasks often involve…
- arXiv cs.AIresearchToward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models
arXiv:2608.01008v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can memorize and disclose sensitive information, motivating machine unlearning to remove designated knowledge while preserving…
- arXiv cs.AIresearchLaCache: Robust Semantic Caching for LLM Serving
arXiv:2608.01718v2 Announce Type: replace Abstract: Semantic caching, reusing responses to answer semantically similar queries, has seen growing adoption in LLM serving, offering faster responses and reduced costs. Yet e…
- arXiv cs.AIresearchSurrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study
arXiv:2608.03172v5 Announce Type: replace Abstract: Structure-preserving de-identification replaces each detected identifier with a realistic same-type surrogate ("Anna S." -> "Maria S.") rather than a tag such as [NAME]…
- arXiv cs.AIresearch$\mathrm{R}{\scriptstyle\mathrm{EAL}}\mathrm{G}{\scriptstyle\mathrm{UARD}}$: Reliable, Efficient, and Auditable LLM Safeguards via Latent Reasoning
arXiv:2608.03838v2 Announce Type: replace Abstract: Reasoning-based large language model (LLM) safeguards improve safety classification accuracy by generating explicit rationales before making decisions. However, generat…
- arXiv cs.AIresearchIllusion of Alignment: Detecting Hidden Disagreement in Collaborative Dialogue
arXiv:2608.08210v2 Announce Type: replace Abstract: Collaborative dialogue can end with apparent agreement while participants still differ on goals, assumptions, or execution plans, creating an \textbf{illusion of alignm…
- arXiv cs.AIresearchAI Model Design and Physician Liability
arXiv:2608.13618v2 Announce Type: replace Abstract: Clinical algorithms can perform differently across patient groups, a concern that grows as these algorithms increasingly take the form of artificial intelligence (AI) m…
- arXiv cs.AIresearchParason: Revealing Subtask and Trial Parallelism in LLM Reasoning
arXiv:2608.24658v2 Announce Type: replace Abstract: Scaling test-time reasoning has substantially improved the problem-solving ability of large language models (LLMs), but standard autoregressive decoding still executes…
- arXiv cs.AIresearchFractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satellite Mega-Constellations: A Wildfire Case Study
arXiv:2609.00875v2 Announce Type: replace Abstract: Satellite mega-constellations are emerging as large-scale sensing, communication, and computation fabrics, yet their learning architectures remain largely inherited fro…
- arXiv cs.AIresearchEmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision
arXiv:2609.02133v2 Announce Type: replace Abstract: Empathetic response generation requires models to decide not only what to say, but also how to respond to the previous speaker's affective situation. We formulate this…
- arXiv cs.AIresearchSTAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation
arXiv:2609.03874v2 Announce Type: replace Abstract: Retrieval Augmented Generation (RAG) is a key component for generating accurate and hallucination free answers using Large Language Models (LLMs). LLMs are improving at…
- arXiv cs.AIresearchStyle Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts
arXiv:2609.08236v2 Announce Type: replace Abstract: Automatic safety judges -- for example Llama Guard, or GPT-4o given a grading prompt -- produce the numbers behind reported jailbreak success rates, defense evaluations…
- arXiv cs.AIresearchNeuSE: Neural SE(3)-Equivariant Embedding for Long-Term Object-Based Simultaneous Localization and Mapping
arXiv:2303.07308v3 Announce Type: replace-cross Abstract: We present NeuSE, a novel Neural SE(3)-Equivariant Embedding for objects, and illustrate how it supports object-based Simultaneous Localization and Mapping (SLAM)…
- arXiv cs.AIresearchLLMRec: Benchmarking Large Language Models on Recommendation Task
arXiv:2308.12241v2 Announce Type: replace-cross Abstract: Recently, the fast development of Large Language Models (LLMs) such as ChatGPT has significantly advanced NLP tasks by enhancing the capabilities of conversationa…
- arXiv cs.AIresearchFast Diffusion-GAN Model for Generating Symbolic Music with Emotions
arXiv:2310.14040v2 Announce Type: replace-cross Abstract: Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis. However, little progre…
- arXiv cs.AIresearchOptimal Transport Aggregation for Distributed Mixture-of-Experts
arXiv:2312.09877v3 Announce Type: replace-cross Abstract: This paper considers the setting in which local Mixture-of-experts (MoE) models are fitted independently on distributed datasets and must be combined into a singl…
- arXiv cs.AIresearchFlowWise: Stateful Fast-Slow Model Serving for Streaming Traffic Intelligence
arXiv:2402.03694v3 Announce Type: replace-cross Abstract: Network traffic analysis in cloud and internet service provider (ISP) networks increasingly relies on machine learning (ML) models, as encryption and service cons…
- arXiv cs.AIresearchTeaching MLP More Graph Information: A Three-stage Multitask Knowledge Distillation Framework
arXiv:2403.01079v2 Announce Type: replace-cross Abstract: We study the challenging problem for inference tasks on large-scale graph datasets of Graph Neural Networks: huge time and memory consumption, and try to overcome…
- arXiv cs.AIresearchPrediction Is All MoE Needs: Expert Load Distribution Goes from Fluctuating to Stabilizing
arXiv:2404.16914v2 Announce Type: replace-cross Abstract: MoE facilitates the development of large models by making the computational complexity of the model no longer scale linearly with increasing parameters. The learn…
- arXiv cs.AIresearchGREAT: A Graph Edge Attention Network for the Electric Vehicle Routing Problem with Asymmetric Costs
arXiv:2408.16717v4 Announce Type: replace-cross Abstract: Due to the ongoing electrification of transportation systems, energy-based routing problems such as the Electric Vehicle Routing Problem (EVRP) are becoming incre…
- arXiv cs.AIresearchPolyrating: A Cost-Effective and Bias-Aware Rating System for LLM Evaluation
arXiv:2409.00696v4 Announce Type: replace-cross Abstract: Rating-based human evaluation has become an essential tool to accurately evaluate the impressive performance of large language models (LLMs). However, current rat…
- arXiv cs.AIresearchScale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
arXiv:2409.12333v2 Announce Type: replace-cross Abstract: Extracting hepatic vessels from abdominal images is of high interest for clinicians since it allows to divide the liver into functionally-independent Couinaud seg…
- arXiv cs.AIresearchIs Complex Query Answering Really Complex?
arXiv:2410.12537v4 Announce Type: replace-cross Abstract: Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks fo…
- arXiv cs.AIresearchReMAP: Lossless Residual Neural Lifting for Scalable MAP Inference in Arbitrary-Order Markov Random Fields
arXiv:2411.18954v5 Announce Type: replace-cross Abstract: Maximum a posteriori inference in a finite Markov random field is generally NP-hard. We study an instance-wise optimizer that minimizes the exact multilinear ener…
- arXiv cs.AIresearchOpen Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription
arXiv:2502.04356v2 Announce Type: replace-cross Abstract: In response to the success of proprietary Large Language Models (LLMs), there is a growing interest in developing open, non-proprietary LLMs and AI foundation mod…
- arXiv cs.AIresearchRandomly Wrong Signals: Bayesian Auction Design with ML Predictions
arXiv:2502.08792v4 Announce Type: replace-cross Abstract: Machine learning can help sellers predict buyers' willingness to pay, but its predictions may be plausible and yet entirely unrelated to a buyer's value. We intro…
- arXiv cs.AIresearchNatural Language Generation from Visual Events: State-of-the-Art and Key Open Questions
arXiv:2502.13034v4 Announce Type: replace-cross Abstract: In recent years, a substantial body of work in visually grounded natural language processing has focused on real-life multimodal scenarios such as describing cont…
- arXiv cs.AIresearchToxicity Is a Property of Communicative Events: A Contextual Stress Measurement Framework for NLP
arXiv:2503.16072v5 Announce Type: replace-cross Abstract: Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet most detectors still t…
- arXiv cs.AIresearchHorizon Scans can be accelerated using novel information retrieval and artificial intelligence tools
arXiv:2504.01627v2 Announce Type: replace-cross Abstract: Introduction: Horizon scanning in healthcare assesses early signals of innovation, crucial for timely adoption. Current horizon scanning faces challenges in effic…
- arXiv cs.AIresearchSAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs
arXiv:2504.08192v3 Announce Type: replace-cross Abstract: Machine unlearning is a promising approach to improve LLM safety by removing unwanted knowledge from the model. However, prevailing gradient-based unlearning meth…
- arXiv cs.AIresearchFPGA-Based Neural Network Accelerators for Space Applications: A Survey
arXiv:2504.16173v4 Announce Type: replace-cross Abstract: Space missions are becoming increasingly ambitious, necessitating high-performance onboard spacecraft computing systems. In response, field-programmable gate arra…
- arXiv cs.AIresearchA Comprehensive Review on RNA Subcellular Localization Prediction
arXiv:2504.17162v2 Announce Type: replace-cross Abstract: The subcellular localization of RNAs, including long non-coding RNAs (lncRNAs), messenger RNAs (mRNAs), microRNAs (miRNAs) and other smaller RNAs, plays a critica…
- arXiv cs.AIresearchGraph Neural Network-Based Reinforcement Learning for Controlling Biological Networks - the GATTACA Framework
arXiv:2505.02712v4 Announce Type: replace-cross Abstract: Cellular reprogramming, the artificial transformation of one cell type into another, has been attracting increasing research attention due to its therapeutic pote…
- arXiv cs.AIresearchTowards Understanding Deep Learning Model in Image Recognition via Coverage Test
arXiv:2505.08814v4 Announce Type: replace-cross Abstract: Deep neural networks (DNNs) play a crucial role in the field of artificial intelligence, and their security-related testing has been a prominent research focus. B…
- arXiv cs.AIresearchLocalizing Persona Representations in LLMs
arXiv:2505.24539v5 Announce Type: replace-cross Abstract: We present a study on how and where personas -- defined by distinct sets of human characteristics, values, and beliefs -- are encoded in the representation space…
- arXiv cs.AIresearchBenchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub
arXiv:2506.00482v2 Announce Type: replace-cross Abstract: LLM benchmarks are often treated as coherent measurement units, yet they are heterogeneous collections of instances spanning diverse domains, skills, formats, and…
- arXiv cs.AIresearchSimulating Student-Tutor Interactions with LLMs for Multilingual Math Feedback
arXiv:2506.04920v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated the ability to generate formative feedback and instructional hints in English, making them increasingly relevant fo…
- arXiv cs.AIresearchGUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models
arXiv:2506.10946v3 Announce Type: replace-cross Abstract: Unlearning large language models (LLMs) is important due to copyright and privacy concerns. A key challenge is unintended forgetting, where removing data inadvert…
- arXiv cs.AIresearchFrom Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs
arXiv:2506.13182v4 Announce Type: replace-cross Abstract: [...] Since then, various APR approaches, especially those leveraging the power of large language models (LLMs), have been rapidly developed to fix general softwa…
- arXiv cs.AIresearchRCStat: A Statistical Framework for using Relative Contextualization in Transformers
arXiv:2506.19549v2 Announce Type: replace-cross Abstract: Identifying which tokens and activations truly influence model predictions is critical for both the efficiency and interpretability of large auto-regressive langu…
- arXiv cs.AIresearchFrom Individuals to Interactions: Benchmarking Gender Bias in Multimodal Large Language Models from the Lens of Social Relationship
arXiv:2506.23101v2 Announce Type: replace-cross Abstract: Ensuring the trustworthiness of Multimodal Large Language Models (MLLMs) requires rigorous evaluation of gender bias, particularly in socially sensitive domains.…
- arXiv cs.AIresearchPhysics-Informed Graph Neural Networks to Reconstruct Local Fields Considering Finite Strain Hyperelasticity
arXiv:2507.05291v2 Announce Type: replace-cross Abstract: We propose a physics-informed machine learning framework called P-DivGNN to reconstruct local stress fields at the micro-scale, in the context of multi-scale simu…
- arXiv cs.AIresearchUnequal Voices: How LLMs Construct Constrained Queer Narratives
arXiv:2507.15585v2 Announce Type: replace-cross Abstract: One way social groups are marginalized in discourse is that the narratives told about them often default to a narrow, stereotyped range of topics. In contrast, de…
- arXiv cs.AIresearchThere are Levels to It: Red Teaming Dialogue With Hierarchical Reinforcement Learning
arXiv:2508.04451v2 Announce Type: replace-cross Abstract: Red teaming is essential for securing Large Language Models, yet current automated methods remain limited by templates and single-turn attacks. To simulate the co…
- arXiv cs.AIresearchOne Size Does Not Fit All: Distribution-Guided Tensor-Wise Adaptive Sparsification for Model Merging
arXiv:2508.06163v2 Announce Type: replace-cross Abstract: Merging multiple task-specific fine-tuned checkpoints into a single multi-task model provides an attractive alternative to joint multi-task training. To mitigate…
- arXiv cs.AIresearchSciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generation with LLMs
arXiv:2508.08742v3 Announce Type: replace-cross Abstract: Scientific literature question answering is a pivotal step towards new scientific discoveries. Recently, \textit{two-stage} retrieval-augmented generated large la…
- arXiv cs.AIresearchPPGFlowECG: Latent Rectified Flow with Cross-Modal Encoding for PPG-Guided ECG Generation and Cardiovascular Disease Detection
arXiv:2509.19774v3 Announce Type: replace-cross Abstract: Electrocardiography (ECG) is the clinical gold standard for cardiovascular disease (CVD) assessment, yet continuous monitoring is constrained by the need for dedi…
- arXiv cs.AIresearchTENET: One Step Toward Test-Driven Development for Repository-Level Code Generation
arXiv:2509.24148v5 Announce Type: replace-cross Abstract: Test-Driven Development (TDD) is a widely adopted practice that requires developers to create and execute tests alongside implementation. With recent advances in…