Research

Latest Research

A running feed of newly published AI research papers, pulled daily from arXiv and filtered by hand before it appears here.

Papers

50 items
Keyword
01PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action ModelsarXiv cs.AIarXiv:2610.25961v2 Announce Type: replace-cross Abstract: Fast and reliable manipulation is crucial for practical robot deployment. Although Vision-Language-Action (VLA) models have recently shown remarkable progress as generalist robot policies, their execution often remains temporally inefficient. A key source of this inefficiency is that policies learn fine-grained temporal patterns from teleoperated demonstrations, requiring many low-level action steps. Temporal action quantization offers a23 Oct 2026↗02TrustAgent-RFF: Agentic Diagnostic Planning for Reliable RF Fingerprinting under Domain ShiftarXiv cs.AIarXiv:2610.24930v2 Announce Type: replace-cross Abstract: Radio frequency fingerprinting (RFF) models can achieve accuracy under source domain conditions but become unreliable when the receiver, distance, collection day, or environment changes. Incorrect predictions in unseen domains may receive high softmax confidence, making confidence thresholding insufficient for trustworthy deployment. We propose TrustAgent-RFF, a prediction level reliability framework for RFF that operates with a frozen i23 Oct 2026↗03Model Capacity Frontier: A Development Framework for LLM-Supported Social SimulationarXiv cs.AIarXiv:2610.24168v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents are increasingly incorporated into agent-based models (ABMs) on the premise that richer, context-sensitive human behavior can improve empirical fidelity. However, LLM-supported ABMs introduce an open-ended design space in which subtle modeling and configuration choices, such as prompt design and environment coupling, can substantially alter outcomes. Developing LLM-supported ABMs to simulate human collec23 Oct 2026↗04Robot Learning with Visual Predicted ForcearXiv cs.AIarXiv:2610.04741v2 Announce Type: replace-cross Abstract: Force-aware manipulation typically relies on specialized force or tactile sensors. We show that force-aware manipulation can instead be achieved through visual force prediction from the deformation of a compliant Fin Ray gripper. Our approach trains two models. First, we train a visual force estimator on calibration data and use it to annotate task demonstrations with force estimates. Second, we train an action--force proposal policy on 23 Oct 2026↗05On the Role of Citations in Preference DataarXiv cs.AIarXiv:2608.21376v2 Announce Type: replace-cross Abstract: Many NLP tasks require systems to provide attribution in their outputs--i.e. citations to grounding sources. Attribution serves as a bulwark against model hallucination and as a means for users to verify the credibility of model outputs. Yet, it is unclear how humans and LLMs evaluate citations when comparing outputs, a process central to reward modeling and modern LLM post-training. This paper studies the role of citations in the prefer23 Oct 2026↗06To Retain or to Adapt? Generalizing Continual LearningarXiv cs.AIarXiv:2607.05609v2 Announce Type: replace-cross Abstract: The Continual Learning (CL) literature has long been driven by the goal of mitigating catastrophic forgetting. This objective rests on an often unstated assumption: that a lifelong learner should approximate the Joint-Task Learning (JTL) solution and retain all previously acquired knowledge. We challenge this retention-centered premise, arguing that in non-stationary environments prioritizing retention can impede real-time adaptation. Sh23 Oct 2026↗07ASPIRE: Agentic /Skills Discovery for RoboticsarXiv cs.AIarXiv:2607.00272v2 Announce Type: replace-cross Abstract: Traditional robot programming is notoriously challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse environment configurations and execution failures. We introduce ASPIRE (Agentic Skill Programming through Iterative Robot Exploration), a continual learning system that autonomously writes and refines robot control programs in a code-as-policy paradigm while compounding experi23 Oct 2026↗08Latent Bridges for Multi-Table Question AnsweringarXiv cs.AIarXiv:2606.28916v3 Announce Type: replace-cross Abstract: We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering. Our method lifts relational data into an heterogeneous graph, encodes it via message passing, and transfers the signals to an LLM through a small set of query-conditioned latent tokens. This provides the LLM with a compact, task-relevant structural representation together with the flattened text. Crucially, the LLM remains strictly frozen to preserve i23 Oct 2026↗09EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge SummariesarXiv cs.AIarXiv:2606.15735v3 Announce Type: replace-cross Abstract: Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for patient readmission, ongoing care, and diagnostic decision-making. When reviewing them, medical experts often must iteratively synthesize information across multiple discharge summaries while verifying the evidence supporting each answer. Although large language models (LLMs) ar23 Oct 2026↗10Closing the Sim-to-Real Gap: An Evaluation Framework for Autonomous Cyber Defense Configuration of Commercial EDRarXiv cs.AIarXiv:2606.08168v2 Announce Type: replace-cross Abstract: Leading commercial endpoint detection and response (EDR) products have shifted from operator-configured rule sets to multi-component systems where autonomous AI components operate alongside, and increasingly in place of, operator-deployed policies. Autonomous defense agents using commercial EDR as their hardening tool are no longer tuning a passive tool, but a black-box autonomous system capable of making vendor-specific decisions. We pr23 Oct 2026↗11Let It Be Simple: One-Step Action Generation for Vision-Language-Action ModelsarXiv cs.AIarXiv:2606.05737v3 Announce Type: replace-cross Abstract: One-step generation from standard diffusion or Flow-Matching training is rarely effective for text-to-image or video generation without distillation or specialized one-step objectives. We find that VLA action generation behaves strikingly differently. Biasing only the training timestep distribution toward the noise endpoint yields strong one-step policies across LIBERO, LIBERO-Plus, LIBERO-Pro, and real-world robot tasks. Moreover, for o23 Oct 2026↗12InfoQuant: Shaping Activation Distributions for Low-Bit LLM QuantizationarXiv cs.AIarXiv:2605.26175v2 Announce Type: replace-cross Abstract: Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activations contain outliers, but that their distributions are often poorly matched to a low-bit uniform quantizer. Existing post-training quantization (PTQ) methods suppress peaks, balance channels, or minimize reconstruction error, yet they rarely specify what activation distribution is actually23 Oct 2026↗13Learning Altruistic Collaboration in Heterogeneous Multi-Team SystemsarXiv cs.AIarXiv:2605.21723v2 Announce Type: replace-cross Abstract: This paper studies heterogeneous multi-team collaboration through dynamic robot allocation, where the robots themselves are treated as transferable resources. Leveraging Hamilton's rule from ecology as an altruistic decision-making mechanism, we propose a multi-team collaborative resource allocation framework with heterogeneous capabilities, transfer costs, and capability-dependent contributions. The resulting general heterogeneous resou23 Oct 2026↗14Feedback World Model Enables Precise Guidance of Diffusion PolicyarXiv cs.AIarXiv:2605.15705v2 Announce Type: replace-cross Abstract: World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable once the robot encounters states outside the training distribution, limiting their effectiveness at deployment. We observe that execution itself provides a natural but underutilized signal: after each action, the robot directly observes the true next state, revealing the mismatch b23 Oct 2026↗15Biological Context Does Not Reliably Improve LLM-Guided Experimental OptimizationarXiv cs.AIarXiv:2605.15341v2 Announce Type: replace-cross Abstract: Autonomous labs increasingly deploy large language models (LLMs) as closedloop biology optimizers that propose a design, read the outcome, then propose again. This is partly because of an assumption that biological knowledge helps an LLM choose better designs than Bayesian optimization, which has no access to biological context. We test that assumption on 45 biology tasks reconstructed from 2,485 experimental rows across 341 published pa23 Oct 2026↗16Deep Reasoning in General Purpose Agents via Structured Meta-CognitionarXiv cs.AIarXiv:2605.11388v2 Announce Type: replace-cross Abstract: Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambiguity through associative judgment, and apply formal procedures to well-specified subproblems. Current LLM agents lack this flexibility, as their scaffolds hard-code such reasoning decisions in advance. These scaffolds are effective when their prescribed structure matches the task, but brittle w23 Oct 2026↗17Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference SimulationarXiv cs.AIarXiv:2605.07985v3 Announce Type: replace-cross Abstract: Selecting the optimal LLM inference configuration requires evaluation across hardware, serving engines, attention backends, and model architectures, since no single choice performs best across all workloads. Profile-based simulators are the standard tool, yet they hardcode their operation set to a specific configuration and re-profile every operation from scratch, making exploration prohibitively expensive. This cost stems from a missing23 Oct 2026↗18ProMORNA: An End-to-End Generative Framework for Full-Length mRNA DesignarXiv cs.AIarXiv:2605.01513v2 Announce Type: replace-cross Abstract: Designing therapeutic messenger RNA (mRNA) requires generating full-length transcripts that optimally balance intracellular stability and translation efficiency. While generative models have advanced mRNA design, existing approaches rely on region-wise generation, expensive inference-time search, or target-specific model updates. To overcome these limitations, we introduce ProMORNA, a zero-shot, end-to-end generative framework for full-l23 Oct 2026↗19SUDP: Secret-Use Delegation Protocol for Agentic SystemsarXiv cs.AIarXiv:2604.24920v4 Announce Type: replace-cross Abstract: Agentic systems now act with user secrets for APIs, messaging platforms, and cloud services. Today's agent runtimes typically implement authorization by exposure: enabling action means placing a reusable secret, or a reusable artifact derived from it, inside the runtime, so a transient prompt-injection or tool-side compromise becomes durable account compromise. Existing defenses cover adjacent pieces such as secret storage, scoped delega23 Oct 2026↗20On the Complementarity of Quantum and Classical Features: Adaptive Hybrid Quantum-Classical Feature Fusion for Breast Cancer ClassificationarXiv cs.AIarXiv:2604.22903v2 Announce Type: replace-cross Abstract: The integration of quantum machine learning with classical deep learning offers promising avenues for medical image analysis by mapping data into high-dimensional Hilbert spaces. However, unifying these paradigms remains challenging due to optimization asymmetries. We propose a hybrid quantum-classical architecture for breast cancer diagnosis based on a dual-branch feature-extraction pipeline. Our framework unifies complementary represen23 Oct 2026↗