AI news archive.
10,659 articles filed under Research, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchAIMO Interpretability Challenge
arXiv:2607.13899v2 Announce Type: replace Abstract: We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models based on the mod…
- arXiv cs.AIresearchIndustryForge-27B: A Domain-Enhanced Multimodal Foundation Model for Industrial CAD
arXiv:2607.28050v2 Announce Type: replace Abstract: Automating industrial CAD design and manufacturing places distinctive demands on multimodal foundation models: the model must see engineering drawings and 3D geometry s…
- arXiv cs.AIresearchEthical LLM-Assisted Research: A Framework for Responsible Delegation, Verification, and Epistemic Value
arXiv:2608.23644v2 Announce Type: replace Abstract: Large language models (LLMs) are becoming routine instruments of scientific research, assisting with literature synthesis, hypothesis development, coding, and formal re…
- arXiv cs.AIresearchER-EDF: A Psychology-Grounded Emotion Regulation Framework for Speech Empathetic Dialogue Generation in Large Audio-Language Models
arXiv:2609.15089v2 Announce Type: replace Abstract: In human conversation, empathy involves not only recognizing a partner's emotion but also regulating it, listeners identify the emotional state, select a suitable regul…
- arXiv cs.AIresearchTaskonomy: Disentangling Task Transfer Learning
arXiv:1804.08328v2 Announce Type: replace-cross Abstract: Do visual tasks have a relationship, or are they unrelated? For instance, could having surface normals simplify estimating the depth of an image? Intuition answer…
- arXiv cs.AIresearchTyphoon: Gradient-Based Task-Specific Masking for Masked Language Models
arXiv:2303.15619v3 Announce Type: replace-cross Abstract: The choice of which tokens to mask is an under-examined design decision in masked language modeling (MLM). Standard pretraining masks tokens uniformly at random,…
- arXiv cs.AIresearchEntropic perspective on AI resilience, data-minimal learning and optimal control
arXiv:2310.14421v5 Announce Type: replace-cross Abstract: Behind the general terms like adversarial attacks and generative adversarial networks (GANs), such criteria as AI resilience and AI robustness gained a crucial im…
- arXiv cs.AIresearchJacobian Descent for Multi-Objective Optimization
arXiv:2406.16232v4 Announce Type: replace-cross Abstract: Many optimization problems require balancing multiple conflicting objectives. To generalize gradient descent, which is limited to single-objective optimization, w…
- arXiv cs.AIresearchDeep learning-based multi-level airway collapse site localization on obstructive sleep apnea patients based on snoring sounds
arXiv:2408.16030v3 Announce Type: replace-cross Abstract: Objective This study evaluated deep learning models, specifically ResNet-50 and Audio Spectrogram Transformer (AST), to identify multi-level upper airway collapse…
- arXiv cs.AIresearchSynergistic Action and Style Priors for Learning Legged Locomotion
arXiv:2410.03246v3 Announce Type: replace-cross Abstract: Deep Reinforcement Learning (DRL) enables robots to learn complex behaviors through interaction with the environment. However, due to the unrestricted nature of t…
- arXiv cs.AIresearchPALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models
arXiv:2503.18462v2 Announce Type: replace-cross Abstract: Deep generative models (DGMs) have caused a paradigm shift in the field of machine learning, yielding noteworthy advancements in domains such as image synthesis,…
- arXiv cs.AIresearchA Survey of Generative Categories and Techniques in Multimodal Generative Models
arXiv:2506.10016v4 Announce Type: replace-cross Abstract: Multimodal generative models (MGMs) have rapidly expanded beyond text generation to encompass images, music, video, human motion, and 3D objects. This survey cate…
- arXiv cs.AIresearchWoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations
arXiv:2508.20976v2 Announce Type: replace-cross Abstract: Large audio-language models (LALMs) extend language understanding into the auditory domain, yet their ability to perform low-level listening, such as pitch and du…
- arXiv cs.AIresearchAttention-Aligned Reasoning for Large Language Models
arXiv:2510.03223v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate st…
- arXiv cs.AIresearchBayesian Nonparametric Dynamical Clustering of Time Series
arXiv:2510.06919v2 Announce Type: replace-cross Abstract: We present a method that models the evolution of an unbounded number of time series clusters by switching among an unknown number of regimes with linear dynamics.…
- arXiv cs.AIresearchOnline Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network
arXiv:2511.01553v3 Announce Type: replace-cross Abstract: Edge AI must adapt to new classes and shifting data within a tight power budget, but online continual learning (learning from each sample before the next arrives)…
- arXiv cs.AIresearchSpectralTrain: A Universal Framework for Hyperspectral Image Classification
arXiv:2511.16084v4 Announce Type: replace-cross Abstract: Hyperspectral image (HSI) classification typically involves large-scale data and computationally intensive training, which limits the practical deployment of deep…
- arXiv cs.AIresearchWhen does Subgroup Balance Matter? Predicting Performance Sensitivity from Latent Separability
arXiv:2512.09496v2 Announce Type: replace-cross Abstract: Unequal representation of demographic groups in training data poses challenges to model generalisation across populations. Standard practice assumes that balancin…
- arXiv cs.AIresearchOPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction
arXiv:2512.13886v3 Announce Type: replace-cross Abstract: Post-training pruning cuts the inference cost of large language models, yet it faces a trade-off: simple heuristics that zero weights are fast but degrade accurac…
- arXiv cs.AIresearchReinforced Linear Genetic Programming
arXiv:2601.09736v2 Announce Type: replace-cross Abstract: Linear Genetic Programming (LGP) is a powerful technique that allows for a variety of problems to be solved using a linear representation of programs. However, th…
- arXiv cs.AIresearchActivation Sensitivity as a Unifying Principle for Post-Training Quantization
arXiv:2601.11663v2 Announce Type: replace-cross Abstract: Post-training quantization (PTQ) methods for large language models compress pretrained weights to low bit-widths without retraining by optimizing layer-local prox…
- arXiv cs.AIresearchExpected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
arXiv:2601.21669v2 Announce Type: replace-cross Abstract: Many reinforcement learning (RL) problems admit multiple terminal solutions of comparable quality, where the goal is not to identify a single optimum but to repre…
- arXiv cs.AIresearchGraph-Theoretic Formulation of Hamiltonian and Ground-State Sign Structures in Heisenberg Antiferromagnets
arXiv:2602.04943v5 Announce Type: replace-cross Abstract: We study Heisenberg antiferromagnets through a graph-theoretic representation of their Hamiltonians. In the computational basis of a fixed-magnetization sector, t…
- arXiv cs.AIresearchCHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning
arXiv:2603.00889v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, largely enabled by supervised fine-tuning (SFT)- and reinforcement learning (RL)-ba…
- arXiv cs.AIresearchAnchoring and Rescaling Attention for Semantically Coherent Inbetweening
arXiv:2603.17651v2 Announce Type: replace-cross Abstract: Generative inbetweening (GI) seeks to synthesize realistic intermediate frames between the first and last keyframes beyond mere interpolation. As sequences become…
- arXiv cs.AIresearchDetection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
arXiv:2603.18280v4 Announce Type: replace-cross Abstract: Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignmen…
- arXiv cs.AIresearchInterpretable PM2.5 Forecasting for Urban Air Quality: A Comparative Study of Adaptive Time-Series Models
arXiv:2603.25495v2 Announce Type: replace-cross Abstract: Accurate short-term air-quality forecasting is essential for public health protection and urban management, yet many recent forecasting frameworks rely on complex…
- arXiv cs.AIresearchAbstract Compression of Conversational Audio Context for LLM-based ASR
arXiv:2603.26246v2 Announce Type: replace-cross Abstract: Standard LLM-based speech recognition systems process utterances in isolation, limiting their ability to leverage conversational context. Here we study whether mu…
- arXiv cs.AIresearchLLaVA-CKD: Bottom-Up Cascaded Knowledge Distillation for Vision-Language Models
arXiv:2605.10641v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (VLMs) are successful in addressing a multitude of vision-language understanding tasks, such as Visual Question Answering (VQA), but…
- arXiv cs.AIresearchDynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
arXiv:2605.10765v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world deployment often requires continual capability expa…
- arXiv cs.AIresearchCounterCount: Diagnosing Knowledge Bias in How Vision-Language Models Count Attributes
arXiv:2605.17826v2 Announce Type: replace-cross Abstract: Do Vision-Language Models (VLMs) count what they see, or what they know about the world? We introduce CounterCount, a diagnostic dataset of paired factual and cou…
- arXiv cs.AIresearchDynamic Model Merging Made Slim
arXiv:2605.18904v2 Announce Type: replace-cross Abstract: Model merging consolidates independently fine-tuned checkpoints without joint training or access to task data. Dynamic methods retain task-specific capacity, but…
- arXiv cs.AIresearchDEFLECT: Temporal Counterfactual Preference Learning for Delay-Robust Asynchronous VLAs
arXiv:2605.19294v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) policies increasingly rely on asynchronous inference to hide model latency behind ongoing robot motion. During inference, the robot c…
- arXiv cs.AIresearchNVIDIA Spectrum-X: Hardware-Accelerated Multiplane Networking for Large-Scale AI Training
arXiv:2605.21187v2 Announce Type: replace-cross Abstract: As distributed model training scales to span hundreds of thousands of GPUs, scale-out networks face unprecedented performance and efficiency demands. NVIDIA Spect…
- arXiv cs.AIresearchWhat a One-Hour Interview Does Not Tell an LLM About You: Interviews Elicit Traits, Not Decision Policies
arXiv:2605.29458v2 Announce Type: replace-cross Abstract: Large language models are increasingly asked to stand in for particular people, and interviewing the person is the natural way to tell a model who they are. We te…
- arXiv cs.AIresearchSame Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models
arXiv:2605.30251v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gradually acros…
- arXiv cs.AIresearchFlow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs
arXiv:2606.10180v2 Announce Type: replace-cross Abstract: We introduce flow control of vision-language-action (VLA) models, a simple and effective way to steer VLA actions in real time through generic inputs, such as a k…
- arXiv cs.AIresearchKITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulation
arXiv:2606.22113v2 Announce Type: replace-cross Abstract: Generalizing manipulation policies across robot embodiments remains difficult because standard policies tie the interactions needed for a task to the actions of a…
- arXiv cs.AIresearchYuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety
arXiv:2606.25034v3 Announce Type: replace-cross Abstract: General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature o…
- arXiv cs.AIresearchProbe, Don't Prompt: A Hidden-State Probe for Metadata Filtering in Multi-Meta-RAG
arXiv:2607.03929v2 Announce Type: replace-cross Abstract: Multi-Meta-RAG improves retrieval for multi-hop question answering by filtering a vector store on metadata, specifically the news source and the publication date,…
- arXiv cs.AIresearchWhen Synthetic Speech Is All You Have: Better Call GRPO
arXiv:2607.08409v2 Announce Type: replace-cross Abstract: LLM-based ASR adapted to regulated domains such as banking is bottlenecked by privacy: real speech is costly and legally constrained to collect, making synthetic…
- arXiv cs.AIresearchDiffEEG: A Self-Supervised Denoising Diffusion Model for Learning EEG seizure-related Representations
arXiv:2607.11578v2 Announce Type: replace-cross Abstract: Deep learning for EEG-based seizure detection faces critical challenges: severe annotation scarcity and extreme class imbalance, where ictal events comprise less…
- arXiv cs.AIresearchDECODEM: Data Extraction from Corporate Organizational Documents via Enhanced Methods
arXiv:2607.15879v3 Announce Type: replace-cross Abstract: Much empirical legal research depends on translating unstructured text into structured variables. In corporate governance research as elsewhere, this translation…
- arXiv cs.AIresearchReducing belief in conspiracy theories as they unfold using large language models
arXiv:2608.06151v2 Announce Type: replace-cross Abstract: The emergence of conspiracy theories in the wake of major events is a significant societal challenge. Here we test whether conversational dialogues with a large l…
- arXiv cs.AIresearchHarnessing Magnitude-Only and Complex Measurements for Improved Dynamic MRI Reconstruction with Learned Priors
arXiv:2608.18036v2 Announce Type: replace-cross Abstract: MRI reconstruction methods for undersampled k-space data naturally utilize complex-valued measurements. Parallel developments in sparse phase retrieval have shown…
- arXiv cs.AIresearchSymmetries and Causality: Causal Effect Identification Beyond IID Data
arXiv:2609.03697v2 Announce Type: replace-cross Abstract: We develop theory for the identification of complex causal queries from non-IID data. We propose a formal description of stochastic systems based on symmetries in…
- arXiv cs.AIresearchWhen Models Edit Too Much: On the Fidelity of Minimal Code Edits
arXiv:2609.04061v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough: useful repairs should also be minimal, reviewable,…
- arXiv cs.AIresearchKnowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views
arXiv:2609.04180v2 Announce Type: replace-cross Abstract: Gaps remain in our understanding of how large language models (LLMs) acquire knowledge during pre-training. We find that auxiliary views, conceptual reformulation…
- arXiv cs.AIresearchAn Empirical Study of Development-Tuned Representation Sensitivity for Medical QA Data Selection
arXiv:2609.09684v2 Announce Type: replace-cross Abstract: We study medical question-answering (QA) data selection when a developer already has questions, labels, and auxiliary explanatory texts but can retain only $B$ ex…
- LessWrongresearchUpdatelessness explained
Introduction This post introduces updatelessness to readers who are familiar with evidential and causal decision theory (EDT and CDT). Roughly, an updateless agent follows the policy that she would have wanted to commit…