Skip to content
THE AI WIREINTELLIGENCE THAT MATTERS
Research

AI research papers

362 papers in Research Sources, newest first, from the research feeds listed on the sources page.

All categoriesResearch Sources · 362Science · 4Frontier Red Team · 3Alignment · 2Societal Impacts · 1Economics · 1
  1. arXivResearch Sources
    Variational Approach for Job Shop Scheduling

    arXiv:2602.00408v3 Announce Type: replace-cross Abstract: This paper proposes a novel Variational Graph-to-Scheduler (VG2S) framework for solving the Job Shop Scheduling Problem (JSSP), a critical task in manufacturing t…

  2. arXivResearch Sources
    HALT: Hallucination Assessment via Log-probs as Time series

    arXiv:2602.02888v2 Announce Type: replace-cross Abstract: Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains.

  3. arXivResearch Sources
    Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models

    arXiv:2602.03994v3 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) prompting is widely used as a reasoning aid and is often treated as a transparency mechanism.

  4. arXivResearch Sources
    PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation

    arXiv:2602.15882v2 Announce Type: replace-cross Abstract: Robot manipulation uses temporal context to select actions and visual foresight to assess their consequences, yet dense representations of past and future observa…

  5. arXivResearch Sources
    Mind the Style: Impact of Communication Style on Human-Chatbot Interaction

    arXiv:2602.17850v3 Announce Type: replace-cross Abstract: Conversational agents increasingly mediate everyday digital interactions, yet the effects of their communication style on user experience and task success remain…

  6. arXivResearch Sources
    MINT: Multimodal Imaging-to-Speech Knowledge Transfer for Early Alzheimer's Screening

    arXiv:2602.23994v2 Announce Type: replace-cross Abstract: Alzheimer's disease is a progressive neurodegenerative disorder in which mild cognitive impairment (MCI) precedes dementia.

  7. arXivResearch Sources
    Universal NP-Hardness of Clustering under General Utilities

    arXiv:2603.00210v2 Announce Type: replace-cross Abstract: Clustering is a central primitive in unsupervised learning, yet practice is dominated by heuristics whose outputs can be unstable and highly sensitive to represen…

  8. arXivResearch Sources
    Enhancing Physics-Informed Neural Networks with Domain-aware Fourier Features: Towards Improved Performance and Interpretable Results

    arXiv:2603.02948v2 Announce Type: replace-cross Abstract: Physics-Informed Neural Networks (PINNs) incorporate physics into neural networks by embedding partial differential equations (PDEs) into their loss function.

  9. arXivResearch Sources
    CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents

    arXiv:2603.03884v2 Announce Type: replace-cross Abstract: Topic localization aims to identify spans of text that express a given topic defined by a name and description.

  10. arXivResearch Sources
    AuthorMix: Modular Authorship Style Transfer via Layer-wise Adapter Mixing

    arXiv:2603.23069v4 Announce Type: replace-cross Abstract: The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original text.

  11. arXivResearch Sources
    AMIGO: Agentic Multi-Image Grounding Oracle Benchmark

    arXiv:2603.28662v2 Announce Type: replace-cross Abstract: Agentic vision-language models increasingly act through extended interactions, but most evaluations still focus on single-image, single-turn correctness.

  12. arXivResearch Sources
    Can We Still Trace L1 Signals? Investigating the Resilience of Native Language Signals in the LLM Era

    arXiv:2604.08568v4 Announce Type: replace-cross Abstract: The widespread use of LLM-based writing assistance has raised an interesting question about the homogenization of English.

  13. arXivResearch Sources
    Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers

    arXiv:2604.11507v2 Announce Type: replace-cross Abstract: Artificial intelligence (AI) is moving increasingly beyond prediction to support decisions in complex, uncertain, and dynamic environments.

  14. arXivResearch Sources
    VISTA: Validation-Informed Trajectory Adaptation via Self-Distillation

    arXiv:2604.12044v2 Announce Type: replace-cross Abstract: Deep learning models may converge to suboptimal solutions despite strong validation accuracy, masking an optimization failure we term Trajectory Deviation.

  15. arXivResearch Sources
    HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark

    arXiv:2604.13954v2 Announce Type: replace-cross Abstract: Existing agent-safety evaluation has focused mainly on externally induced risks.

  16. arXivResearch Sources
    Schema-Key Wording as an Instruction Channel in Structured Generation under Constrained Decoding

    arXiv:2604.14862v3 Announce Type: replace-cross Abstract: Constrained decoding is widely used to make large language models produce structured outputs that satisfy schemas such as JSON.

  17. arXivResearch Sources
    How to Compress KV Cache in RL Post-Training? Shadow Mask Distillation for Memory-Efficient Alignment

    arXiv:2605.06850v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) has emerged as a crucial paradigm for unlocking the advanced reasoning capabilities of Large Language Models (LLMs), encompassing fram…

  18. arXivResearch Sources
    EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control

    arXiv:2605.16692v3 Announce Type: replace-cross Abstract: We introduce EfficientTDMPC, a sample-efficient model-based reinforcement learning method for continuous control built on the TD-MPC family of algorithms.

  19. arXivResearch Sources
    Detect Before You Leap: Mirage Detection in Vision-Language Models

    arXiv:2606.00435v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) can produce confident answers without relevant visual evidence, a failure mode known as mirage reasoning (Asadi et al., 2026).

  20. arXivResearch Sources
    Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation

    arXiv:2606.01670v2 Announce Type: replace-cross Abstract: Recently, Generative Recommenders (GRs) have emerged as a transformative recommendation paradigm by replacing traditional item IDs with semantic indices (SIDs).

  21. arXivResearch Sources
    Libra: Efficient Resource Management for Agentic RL Post-Training

    arXiv:2606.03077v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has emerged as a standard post-training paradigm for shaping large language models (LLMs) into capable agents.

  22. arXivResearch Sources
    FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement

    arXiv:2606.03852v2 Announce Type: replace-cross Abstract: Large language models often generate code with bugs.

  23. arXivResearch Sources
    From 'May' to 'Is': Certainty Distortion in Language Model Rewriting

    arXiv:2606.07951v2 Announce Type: replace-cross Abstract: Humans increasingly turn to Language Models (LMs) in ways that shape beliefs and drive decisions, including discussing, rewriting, and summarizing information fro…

  24. arXivResearch Sources
    LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models

    arXiv:2606.09430v2 Announce Type: replace-cross Abstract: Online task-free continual learning (TFCL) requires intelligent agents to sequentially accumulate knowledge from an unbounded, non-stationary data stream under st…

  25. arXivResearch Sources
    Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens

    arXiv:2606.16847v5 Announce Type: replace-cross Abstract: Diffusion Large Language Models (dLLMs) offer a promising avenue for parallel generation but face a trade-off between decoding speed and quality.

  26. arXivResearch Sources
    SegTME-UNI2: A Foundation Model-Based Framework for Generalisable Multiclass Cell Segmentation and LLM-Driven Tumour Microenvironment Characterisation in Histopathology

    arXiv:2606.17702v3 Announce Type: replace-cross Abstract: Characterising the TME from routine H&E-stained histology images requires simultaneous cell segmentation, biological feature extraction, and interpretable clinica…

  27. arXivResearch Sources
    Subjective Risk Decomposition: A New View for Uncertainty Quantification

    arXiv:2607.15196v3 Announce Type: replace-cross Abstract: We present a novel viewpoint for uncertainty quantification.

  28. arXivResearch Sources
    Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling

    arXiv:2607.15740v3 Announce Type: replace-cross Abstract: As Text-to-Image (T2I) systems rapidly advance, evaluating the cultural authenticity of synthesized content has become increasingly important for fair and trustwo…

  29. arXivResearch Sources
    Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents

    arXiv:2607.19190v4 Announce Type: replace-cross Abstract: Real-to-sim conversion for robotic interaction with objects remains labor-intensive because it requires more than visual reconstruction: a streamlined real2sim pr…

  30. arXivResearch Sources
    Riemannian Deep Learning: Modules, Networks, and Geometries

    arXiv:2607.19305v4 Announce Type: replace-cross Abstract: Deep neural networks on manifold-valued representations have attracted growing interest, but many basic components remain tied to specific manifolds, rely on Eucl…

  31. arXivResearch Sources
    Post-Training in Time Series Foundation Models: A Unifying Framework

    arXiv:2607.20002v3 Announce Type: replace-cross Abstract: Time series foundation models (TSFMs) have emerged as general-purpose models for time series analysis, but pretraining alone is often insufficient for reliable do…

  32. arXivResearch Sources
    Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization

    arXiv:2608.00569v3 Announce Type: replace-cross Abstract: Deploying billion-parameter Vision-Language-Action (VLA) policies on mobile robots creates a systems conflict: semantic reasoning benefits from cloud GPUs, wherea…

  33. arXivResearch Sources
    Ranking Infrared-Visible Fusion the Way Humans Do: A Learned Pairwise Preference Measure

    arXiv:2608.01301v4 Announce Type: replace-cross Abstract: Human pairwise comparison provides a direct basis for perceptual infrared-visible image fusion assessment, but dense annotation becomes costly as method pools gro…

  34. arXivResearch Sources
    Deep Divide-and-Reduce in Symbolic Regression

    arXiv:2608.02628v3 Announce Type: replace-cross Abstract: Symbolic regression (SR) aims to discover underlying mathematical expressions from data while preserving interpretability.

  35. arXivResearch Sources
    Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models

    arXiv:2608.04765v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models provide a unified paradigm for connecting visual perception, language understanding, and robotic control.

  36. arXivResearch Sources
    Governing Agentic AI in FinTech

    arXiv:2608.11344v3 Announce Type: replace-cross Abstract: Financial institutions are delegating consequential decisions to agentic AI systems that decompose goals, coordinate models and tools, and act with little oversig…

  37. arXivResearch Sources
    Unsupervised Anomaly Detection for Image Dataset Quality Assurance in Multi-Center Breast MRI

    arXiv:2608.16725v2 Announce Type: replace-cross Abstract: Corrupted, inconsistent, or anomalous data silently threatens the safety and reliability of medical AI.

  38. arXivResearch Sources
    Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents

    arXiv:2608.27141v5 Announce Type: replace-cross Abstract: Large language model agents are increasingly deployed as autonomous loops.

  39. arXivResearch Sources
    Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and Shuffling

    arXiv:2609.01232v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) are increasingly used in split-inference systems, where edge devices transmit intermediate token representations to a remote cloud.

  40. arXivResearch Sources
    Not All Agreement Counts as Corroboration: Provenance-Conserving Multi-View Fusion for Typed Action Admission in Human-Robot Collaboration

    arXiv:2609.01662v2 Announce Type: replace-cross Abstract: Better probability scores do not establish that evidence has been counted correctly.

  41. arXivResearch Sources
    Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing Data

    arXiv:2609.03391v2 Announce Type: replace-cross Abstract: Contrastive language-image learning (CLIP) has become a key paradigm for remote sensing vision-language understanding.

  42. arXivResearch Sources
    Calendar-Structured Sparse Principal Component Analysis for Interpretable Multi-Periodic Electricity Consumption Profiles

    arXiv:2609.06060v2 Announce Type: replace-cross Abstract: Long-term electricity-consumption profiles exhibit several simultaneous periodic structures, including daily, weekly, and annual cycles.

  43. arXivResearch Sources
    Steering Interference Reflects the Model's Defaults, Not the Behavior Directions

    arXiv:2609.06951v2 Announce Type: replace-cross Abstract: Activation steering promises modular control of language model behavior: a behavior such as politeness corresponds to a direction in a model's activations, and ad…

  44. arXivResearch Sources
    Proprioception-Anchored Cross-Modal Pretraining for Zero-Shot Sim-to-Real Contact-Rich Assembly

    arXiv:2609.07534v3 Announce Type: replace-cross Abstract: Contact-rich assembly remains challenging because it requires submillimeter spatial accuracy and reliable interpretation of forces during sustained contact.

  45. arXivResearch Sources
    Adaptive Anisotropic Attention for Axis-Structured Signals

    arXiv:2609.08788v3 Announce Type: replace-cross Abstract: Dense self-attention treats all token pairs as equally plausible before learning, an interaction-isotropic prior that can be mismatched to structured signals.

  46. arXivResearch Sources
    A Mathematical Theory of Pragmatic Information

    arXiv:2609.10986v2 Announce Type: replace-cross Abstract: We propose a mathematical theory of pragmatic information that connects communication, control, and decision-making.

  47. arXivResearch Sources
    Creating an Atomic User Model for Personality-Aware Large Language Model Interaction

    arXiv:2609.12086v2 Announce Type: replace-cross Abstract: Assistants built on large language models are expected to write in their users' own voice.

  48. arXivResearch Sources
    Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks

    arXiv:2609.12839v3 Announce Type: replace-cross Abstract: The proliferation of highly capable open-weight Small Language Models (SLMs) democratizes access to advanced cybersecurity capabilities, posing an escalating risk…

  49. arXivResearch Sources
    Language-Guided Terrain-Adaptive Neural MPC for Autonomous Traversal of Articulated Tracked Robots

    arXiv:2609.13083v3 Announce Type: replace-cross Abstract: In urban search and rescue, articulated tracked robots (ATRs) must traverse structured but contact-rich environments such as stairwells and cluttered building int…

  50. arXivResearch Sources
    Cross-Block Conditioning in Deep Boltzmann Machines for Statistical Data Fusion

    arXiv:2609.14934v2 Announce Type: replace-cross Abstract: Statistical data fusion combines two panels that share a block of covariates but observe disjoint outcome blocks, and in its traditional form no row observes both…