arXiv:2607.17365v1 Announce Type: cross
Abstract: High-contrast imaging demands extremely sensitive wavefront sensing to correct atmospheric effects and surface errors. While the limits of the sensitivity of a wavefront sensor are well known, a practical, robust design that saturates these limits remains elusive. This work further investigates the PIAA-ZWFS (Phase-Induced Amplitude Apodization-Zernike Wavefront Sensor). In previous work, we developed a framework to optimise its design, maximising Fisher information per frame in the presence of phase aberrations. In these proceedings, we study the effect of various manufacturing and alignment errors in the system on the overall performance. We employ both traditional Monte Carlo sampling and a 2nd order expansion using our auto-differentiable simulator. The performance of the PIAA-ZWFS is not significantly degraded by these errors at values typical for manufacturing.
Science Journals
arXiv:2507.05278v4 Announce Type: replace
Abstract: The TRIUMF Ultracold Advanced Neutron (TUCAN) collaboration has been developing a high-intensity ultracold neutron (UCN) source aimed at searching for the neutron electric dipole moment (EDM) with a sensitivity goal of $10^{-27}\ e{\rm cm}$. This article reports on recent progress in commissioning of the UCN source and in the development of the neutron EDM spectrometer. In its final configuration, the accelerator-driven super-thermal UCN source will enable a neutron EDM experiment with two orders of magnitude improved statistics compared to the current best experiment. Substantial progress in 2024 allowed the collaboration to operate the complete source system, with the exception of the liquid deuterium cold moderator, resulting in the first production of UCNs. The status of the EDM spectrometer is also presented, with emphasis on UCN handling components and magnetic subsystems relevant to field control, shielding, and magnetometry.
arXiv:2602.01131v2 Announce Type: replace
Abstract: With the rapid expansion of the low-altitude economy, Unmanned Aerial Vehicles (UAVs) serve as pivotal aerial base stations supporting diverse services from users, ranging from latency-sensitive critical missions to bandwidth-intensive data streaming. However, the efficacy of such heterogeneous networks is often compromised by the conflict between limited onboard resources and stringent stability requirements. Moving beyond traditional throughput-centric designs, we propose a Sensing-Communication-Computing-Control closed-loop framework that explicitly models the impact of communication latency on physical control stability. To guarantee mission reliability, we leverage the Lyapunov stability theory to derive an intrinsic mapping between the state evolution of the control system and communication constraints, transforming abstract stability requirements into quantifiable resource boundaries. Then, we formulate the resource allocation problem as a Stackelberg game, where UAVs (as leaders) dynamically price resources to balance load and ensure stability, while users (as followers) optimize requests based on service urgency. Furthermore, addressing the prohibitive computational overhead of standard Deep Reinforcement Learning (DRL) on energy-constrained edge platforms, we propose a novel and lightweight pruning-based Proximal Policy Optimization (PPO) algorithm. By integrating a dynamic structured pruning mechanism, the proposed algorithm significantly compresses the neural network scale during training, enabling the UAV to rapidly approximate the game equilibrium with minimal inference latency. Simulation results demonstrate that the proposed scheme effectively secures control loop stability while maximizing system utility in dynamic low-altitude environments.
arXiv:2605.31581v2 Announce Type: replace
Abstract: The same arguments often need to be evaluated under different external regimes. An agent with influence over the regime has a strategic lever that standard formalisms do not directly capture. We introduce context-dependent argumentation frameworks (CDAFs), an extension of Dung's theory in which a defeat function determines, per context, which attacks succeed. Blocked attacks are inverted rather than deleted, so extensions stay conflict-free with respect to the attack relation. A perspective-labeled specialisation derives the defeat function from a relevance set $\rho$ and a priority $\pi$. The relevance set is the agent's action space. In a small worked example, the agent's target argument is rejected under every full-relevance priority, yet accepted under a partial activation whose outcome no VAF audience can mirror. We define the corresponding decision problem, ACTIVATION-MANIPULATION, and record baseline complexity bounds. For grounded semantics with mandatory perspectives the problem is NP-complete, and the hardness comes from the activation choice itself.
arXiv:2606.02780v3 Announce Type: replace
Abstract: The success of the transformer architecture as the backbone of modern LLMs is in large part due to its use of attention layers. An attention layer follows the standard neural network paradigm: it takes the residual stream as input and thereby produces context-dependent query, key, and value vectors. However, we find that model performance meaningfully improves when deeper layers learn only a context-free value vector to preserve the original token information, without drawing on any context from the residual stream. When the model has access to this context-free value vector, adding back the context-dependent component provides little additional benefit for aggregate benchmark performance. Such context-free value vectors can be stored as sparse model parameters, eliminating the need to recompute or persistently cache these values. Through systematic ablations on the key design choices for such context-free value vectors, we propose Bank of Values (BoV), a new way of computing value vectors in attention by learning a lookup table of token-specific value vectors for each of the last third of layers. Across 135M and 780M models, BoV improves validation loss over standard attention and, at 780M, the average score across 21 benchmarks, matching the previous best method that adds token information to the value vector with less compute and memory.
arXiv:2606.04257v2 Announce Type: replace
Abstract: Monroe (2026) shows that, if no optimal proof system exists, then every sound arithmetic theory S extending S^1_2 with polynomial-time decidable axioms fails, for all sufficiently large k, to simulate S^1_2+phi_BB(k), where phi_BB(k) asserts the exact k-state Busy Beaver value. This gives the nonexistence hypothesis an information-constraint interpretation through canonical hard instances. If the best-known route to simulation is also necessary--namely, if simulation requires a relative-consistency explanation over a weak base--then the same constraint applies to inaccessible Kolmogorov-randomness facts. We call this conjecture Kolmogorov Hardness (KH).
Finite-scale and hierarchy-level forms of KH yield, conditionally, dense families of small hard tautologies, PH noncollapse with explicit dense separators, and SAT notin P/poly. Under separately stated assumptions, variants yield P-inseparability of a disjoint NP pair, no mutual help between mutually conditionally random axioms, one-way functions via Liu--Pass, derandomization, and Feige-style random-refutation hardness. Allender et al. provide a complementary calibration: full access to conventional random-string oracles supports every PSPACE computation, whereas any fixed sound computably axiomatized theory can certify only finitely many positive randomness instances.
The framework organizes complexity conjectures around canonical information constraints. It seems self-evident that efficient proofs should not leverage true randomness facts unavailable to the proving theory. Yet KH may be independent of standard metatheories: it resembles reflection, can fail internally in nonstandard models even when externally true, and may constrain the metatheories themselves. We propose a research program on extensions, self-evidence, formal independence, and possible new axioms.
arXiv:2606.04460v2 Announce Type: replace
Abstract: AI has the potential to transform cybersecurity by enabling systems that can autonomously detect, analyze, and remediate software vulnerabilities. However, existing cybersecurity evaluations of AI systems are limited in scale or scope, and fail to capture the end-to-end lifecycle of real-world software vulnerability discovery and remediation. To address this gap, we propose CyberGym-E2E, a large-scale and realistic end-to-end cybersecurity benchmark that comprehensively evaluates AI agents' abilities across the full lifecycle of vulnerability discovery, PoC generation, and patch generation. CyberGym-E2E is comprehensive and scalable, as we build an automated, agent-enhanced pipeline for transforming open-source vulnerability data into realistic evaluation environments. Currently, the benchmark consists of 920 real-world vulnerabilities across 139 different open-source projects.
arXiv:2606.05558v2 Announce Type: replace
Abstract: Evaluating large language model (LLM) agents in multi-turn interactive environments is expensive and risky, as it requires online environment interaction. We propose ADWM (Autoregressive Diffusion World Model), an evaluation framework that estimates the performance of a new LLM agent policy purely from pre-collected trajectories. The core idea is to learn a latent diffusion world model that simulates how the environment responds to the evaluation policy, without ever executing it in the real environment. Existing diffusion-based OPE methods guide full trajectories in a single pass by jointly diffusing states and actions, an assumption that breaks down for LLM agents whose actions are discrete text that must be sampled from the policy after observing the environment. Unlike autoregressive world models that suffer from compounding errors, ADWM models each transition as an independent denoising process, enabling reliable step-by-step rollouts where the world model and agent alternate in causal order. Crucially, the LLM agent under evaluation directly guides the diffusion generation at each step via a policy-conditioned score function, ensuring that simulated trajectories accurately reflect its decision-making patterns. Empirically, ADWM achieves accurate value estimates and evaluation reliability across diverse multi-turn agent tasks, demonstrating its promise as a practical framework for offline LLM agent evaluation.
arXiv:2606.06197v3 Announce Type: replace
Abstract: Question answering (QA) systems have achieved notable progress with the advent of large language models (LLMs). However, they still face challenges in accurately extracting and generating precise answers from given contexts, particularly when dealing with complex or ambiguous queries. Existing approaches often struggle with contextual understanding, answer consistency, and generalization across diverse domains. In this work, we propose a question answering system based on large language models, where the input consists of a textual context and a corresponding question, and the output is a concise and accurate answer. The motivation behind this research lies in addressing the limitations of current QA systems, particularly their tendency to produce irrelevant or imprecise responses despite having access to the correct context. Our methodology involves fine-tuning a pre-trained LLM on a benchmark QA dataset to improve its contextual comprehension and answer extraction capabilities. Specifically, we utilize the Stanford Question Answering Dataset (SQuAD1.1), which provides high-quality context-question-answer triplets for supervised training and evaluation. Experimental results show that the fine-tuned Roberta-base model achieves the highest performance, attaining a ROUGE-L score of 86.84%, a BLEU score of 28.24%, and a BERTScore of 95.38%. These results indicate strong accuracy and answer relevance, demonstrating the effectiveness of the proposed approach for context-based question answering tasks. Furthermore, the findings confirm that targeted fine-tuning substantially improves the reliability and precision of QA systems.
arXiv:2606.06491v2 Announce Type: replace
Abstract: Robot manipulation alternates between low-risk transit phases that call for fast execution and high-risk contact stages that demand slow, precise motion. Yet existing Vision-Language-Action models (VLAs) only inherit a single fixed speed from training demonstrations. Prior efforts to accelerate VLAs through model compression, KV-cache reuse, or reinforcement learning only shift the policy from one fixed speed to another, and leave deceleration almost unexplored. We observe that the magnitude of each predicted action already governs how fast the robot moves, opening a direct route to controllable execution speed. We turn this observation into TempoVLA, a single VLA whose execution speed is controlled by an explicit condition. TempoVLA combines two coupled components. (1) A data-side Variable-Speed Trajectory Augmentation (VSTA) that re-times demonstration to any target speed by merging or splitting actions while preserving its motion semantics. (2) A model-side conditioning mechanism that feeds the speed to the policy. Statistics show that VSTA reaches the requested speed with negligible motion error. Experiments in simulation and on real-world tasks demonstrate that TempoVLA achieves flexible speed control in both directions, while VSTA additionally boosts the default $1\times$ performance via better data utilization. Furthermore, by cooperating with a large multimodal model, TempoVLA realizes dynamic speed control, accelerating through low-risk phases and decelerating for high-risk ones.
arXiv:2606.06752v2 Announce Type: replace
Abstract: In this industrial experience paper, we present Pomona, a lightweight agentic tool that utilises agent skills for continuous code quality improvement. Inspired by the Kaizen (TM) philosophy, Pomona automates a cycle of discovery and incremental repair: a Scanning skill identifies tasks and prioritises them in a backlog, while a Repair skill generates small, easily reviewable pull requests (PRs). This design enables frequent, low-risk improvements while maintaining engineer trust and reducing technical debt. We evaluated Pomona at Bloomberg through a three-month team deployment and a questionnaire distributed to senior engineers. The results are promising: 32/39 PRs (82.1%) were merged with a median time-to-close of just over two hours. Moreover, 10/12 surveyed engineers expressed a desire to adopt Pomona, praising its small diff sizes and focus on code quality. Since our evaluation, another team has adopted Pomona. We conclude with actionable insights for deploying agents in industry.
arXiv:2606.07557v2 Announce Type: replace
Abstract: Decentralized multi-agent swarm coordination remains fundamentally challenged by the combinatorial scaling of joint action spaces and high-overhead training or optimization loops when managing localized group behaviors. To address this problem from a different perspective, this paper introduces the Swarm Policy Interference Network (SPIN) framework, which models multi-agent communication topologies as compressed tensor networks. By factorizing the joint policy tensors of local multi-agent cliques into Open Boundary Condition Matrix Product State (MPS) chains, SPIN replaces explicit exponential joint-action enumeration with clique-level contractions that scale linearly in clique length for fixed local behavior and bond dimensions. To connect raw spatial geometry with this discrete algebraic backend without relying on online training loops, we introduce a decoupled framework combining a lightweight frozen neural mapper evaluated offline with a deterministic zero-shot importance-reweighting filter based on the Radon-Nikod\'ym derivative. We evaluate an executable prototype of this framework within a simulation experiment across distinct task regimes: single-target tracking, decentralized area coverage, and structured multi-goal coordination. The results demonstrate that SPIN functions as a reusable decentralized coordination layer across tracking, dispersion / area coverage, and structured multi-goal coordination, with its strongest gains appearing in multi-goal coordination and dense local interaction regimes, without requiring scenario-specific online optimization or retraining.
arXiv:2606.07559v2 Announce Type: replace
Abstract: Fine-tuning a language model often fails silently when its correct completion must outrank a near-synonym competitor. Cross-entropy loss falls monotonically while the correct token never overtakes the competitor. We study five transformer architectures of two families over a fivefold parameter range, on ten contexts where the correct completion and nearest competitor overlap substantially. We construct an order parameter combining the predicted distribution with the geometric overlap between token embeddings. The density-matrix formulation is natural because the prediction distribution lives over a non-orthogonal embedding basis. It decomposes additively into a signal, tracking commitment to the correct token over its nearest competitor, and a background drag, set by how the embedding bulk leaks probability into the score. This isolates two failure modes. In kinematic failure the signal stays small and the model never commits. In structural failure the drag actively worsens as fine-tuning proceeds and the model degrades geometrically even as its loss decreases. Sharp jumps resemble phase transitions but are not. Tracking it after every gradient step rules out spontaneous symmetry breaking. Under LoRA fine-tuning the embedding matrix is frozen, so no geometric phase transition is possible and the discontinuity lies in the softmax readout. One dimensionless quantity is consistent across all five models under full fine-tuning, while a second sorts them into two classes by bulk embedding distribution and predicts whether LoRA alone can drive a sentence to commit. As a blind test, the framework predicts the critical learning rate of a held-out architecture, used to fit no parameter, to within 2.1% of a subsequent sweep. All findings concern the near-synonym geometric mechanism studied here and should not be extrapolated without re-calibration to instruction tuning or broader tasks.
arXiv:2606.07939v2 Announce Type: replace
Abstract: Research on artificial intelligence and work assigns each occupation a single exposure score. We build an instrument to see what those scores average over: a decomposition of 1,961 O*NET work activities into 15,817 atomic micro-actions by a consensus multi-agent LLM pipeline, clustered from text alone into seven semantic classes. Projecting exposure indicators onto these classes reveals two extreme poles, tool-mediated physical execution and planning-and-design, separated by a gap far larger than random partitions of the same data produce (permutation $P < 10^{-4}$; Cliff's $\delta = 0.80$ under our tech-risk index and $0.90$ under GPT-4 task ratings). The poles flank a broad central band that carries most work and is only weakly more compressed than chance. The poles are stable across clustering resolution, sentence encoder (under a common partition), and indicator, yet which pole is most exposed has inverted since 2013: the two extremes swap identity between the Frey-Osborne computerisation era and the LLM era, and at the occupation level an occupation's 2013 automatability declines as its linguistic content rises ($\rho = -0.40$, $n = 618$). We release the instrument and its outputs. The durable object for forecasting is the structure of work itself, not any era's exposure ranking.
arXiv:2606.08012v2 Announce Type: replace
Abstract: The oracle problem, broadly understood as the difficulty of reliably incorporating external information into blockchain-based systems, has been widely examined by scholars and practitioners. Recent comparative research has shown that several challenges of modern blockchain oracles, including attributability, accountability, integrity, and query design, mirror procedural and epistemic constraints already present in ancient oracular institutions such as the Delphic Oracle. Yet the translation of these insights into applied oracle design remains largely unexplored. This paper introduces the Dodona Protocol, a modular, chain-agnostic oracle service inspired by procedural patterns identified in ancient and modern oracle systems. Named after the Oracle of Zeus at Dodona, one of the oldest oracular sanctuaries in ancient Greece, the protocol operationalizes principles such as structured consultation, access control, attributable resolution, constrained query formats, reputational accountability, and tiered service availability. Its first module implements a query and dispute resolution mechanism in which a named expert resolver provides binding answers to structured questions submitted by petitioners. The oracle does not claim to reveal objective truth; rather, it produces outcomes that parties have agreed in advance to accept. The paper presents the design rationale, architecture, and comparative positioning of the Dodona Protocol. It frames the protocol as a living research experiment within the Design Science Research tradition, where the deployed system functions as the research artifact and operational data support structured analysis, iterative refinement, and peer-reviewed dissemination. In doing so, the paper seeks to bridge the gap between oracle theory and oracle practice.
arXiv:2607.18053v1 Announce Type: new
Abstract: Polarization-encoded optical-fiber links provide a useful platform for investigating the coexistence of communication and sensing functions in a shared optical channel. In this work, a classical analog of the BB84 polarization-encoding scheme was implemented over a bend-insensitive fiber link to evaluate how temperature, axial strain, and torsion affect the transmitted state of polarization and the recovery of a binary key. Temperature variations from 24 {\deg}C to 35 {\deg}C and axial strain up to 2 m{\epsilon} produced only minor polarization-state variations and did not affect key recovery. In contrast, fiber torsion induced a pronounced retarder-like evolution of the state of polarization, reducing the detector-intensity contrast used for bit discrimination and degrading key recovery. For intermediate torsion angles, the erasure rate reached 50%. The polarization state tended to recover for rotations close to {\Delta}{\theta} = 180{\deg}, consistent with the oscillatory response observed on the Poincar\'e sphere. These results identify torsion as the dominant impairment in the tested polarization-encoded fiber link and demonstrate its potential use as a sensing mechanism in integrated communication-and-sensing architectures.
arXiv:2607.17644v1 Announce Type: new
Abstract: Multi-head Latent Attention (MLA) ships two implementations in Megatron-Core: an explicit form used for training and an absorbed form -- which slashes collective communication by gathering only the compressed latent -- that is fully implemented but hard-asserted out of training (the forward opens with "assert not (self.training and self.cache_mla_latents)"), allowed only in inference decode. The library documents no reason. We show the restriction is well-founded and quantify why: ported to training, the absorbed form is a memory trap -- its intermediates live in n_h x d_kv dimensions per token, larger than the per-head K/V they replace -- inflating activation memory by 20-34%, up to 9.2 GB at DeepSeek-V3 scale (n_h=128, seq=16384, SP=8, eager kernel; the gap widens to 19.2 GB under a fused kernel), enough to change device-fit. This measurement, validated on two axes (linear in seq and n_h) and cross-verified on NVIDIA A100, explains the otherwise-undocumented restriction and leaves practitioners with no low-communication MLA training path. We then provide one. LAGA (Latent All-Gather Attention) keeps the absorbed form's latent-gather communication but rejects the absorb reformulation, instead reconstructing per-head K/V locally from the gathered latent. On 8x Ascend 910B at real DeepSeek-V3 dimensions, LAGA cuts collective communication 1.98x, matches explicit memory within 0.5%, is bit-identical to explicit at SP=1 and equivalent to within 1e-3 at SP=2-8, and under a fused attention kernel improves attention-block throughput 1.04-1.06x single-node and 1.07-1.24x cross-node -- leading at all sequence lengths in the cross-node regime MLA is deployed for.
arXiv:2607.18081v1 Announce Type: new
Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across a range of Natural Language Processing (NLP) tasks, but their high computational and memory demands pose significant challenges for deployment on resource-constrained edge devices. Existing approaches to model compression and optimization often rely on coarse-grained pruning or quantization, which can compromise accuracy or require re-training and fine-tuning. In this work, we introduce SelectInfer, a neuron-level optimization framework that enables efficient LLM inference on edge devices through selective neuron loading and computation. By profiling and identifying both task-specific and general-purpose neurons using an offline LLM profiler, SelectInfer implements two key optimizations: selective loading, which reduces memory footprint by selectively loading a subset of neurons that were identified to be most important during the offline stage, and selective computation, which dynamically computes only the most relevant neurons at runtime. Evaluation across multiple datasets shows that SelectInfer achieves significant reductions in memory footprint and computation while preserving task performance, making it a practical step towards enabling LLM deployment on edge devices
arXiv:2511.08423v4 Announce Type: replace
Abstract: A truly universal AI-Generated Image (AIGI) detector must simultaneously generalize across diverse generative models and varied semantic content. Current methods learn a single, entangled forgery representation, conflating content-dependent flaws with content-agnostic artifacts, and are further constrained by outdated benchmarks. We propose OmniAID, a novel framework centered on a decoupled Mixture-of-Experts (MoE) architecture that separates: (1) semantic flaws across distinct content domains via Routable Specialized Semantic Experts, and (2) content-agnostic universal artifacts from content-dependent flaws via a Fixed Universal Artifact Expert. A two-stage training strategy first specializes experts independently with domain-specific hard-sampling, then trains a lightweight gating network for effective input routing. By explicitly decoupling "what is generated" (content-specific flaws) from "how it is generated" (universal artifacts), OmniAID achieves robust generalization. We also introduce Mirage, a large-scale, contemporary dataset comprising a modern training set and a challenging test set. Extensive experiments demonstrate that OmniAID surpasses existing detectors, establishing a new standard for AIGI detection against modern, in-the-wild threats. Code is available at https://github.com/yunncheng/OmniAID.
arXiv:2602.13811v2 Announce Type: replace
Abstract: Physics-Informed Neural Networks present a novel approach in SciML that integrates physical laws in the form of partial differential equations directly into the NN through soft constraints in the loss function. This work studies the application of PINNs to solve a one dimensional coupled electro-elastodynamic system modeling linear piezoelectricity in stress-charge form, governed by elastodynamic and electrodynamic equations. Our simulation employs a feedforward architecture, mapping space-time coordinates to mechanical displacement and electric potential. Our PINN model achieved global relative L2 errors of 2.34 and 4.87 percent for displacement and electric potential respectively. The results validate PINNs as effective mesh free solvers for coupled time-dependent PDE systems, though challenges remain regarding error accumulation and stiffness in coupled eigenvalue systems.
arXiv:2607.18106v1 Announce Type: new
Abstract: Methods for discovering rare failures in autonomous systems have so far been demonstrated almost exclusively in simulations with simple, academic driving stacks, leaving open whether they generalize to the more robust planners used in commercial systems. We address this gap by applying two rare-event discovery algorithms to a commercial autonomous trucking stack. Adaptive stress testing (AST) uses reinforcement learning to search for the most likely noise trajectories leading to a simulated collision, while diffusion-based failure sampling (DiFS) trains a denoising diffusion model to sample a diverse set of failures. We show that both algorithms find simulated collisions during merge and cut-in maneuvers where traditional Monte Carlo simulation does not. To make these failures actionable, we introduce a statistical analysis based on principal component analysis (PCA) that classifies failures into common modes and identifies the timesteps that most influence the outcome. We cluster the principal components and invert the PCA transform to recover generalized noise trajectories, and show that these trajectories reproduce failures in identical and similar scenarios. This provides a path from failure discovery to systematic diagnosis of perception-level flaws.
arXiv:2503.12562v2 Announce Type: replace
Abstract: In Multiple Object Tracking (MOT), Re-identification (ReID) features are widely employed as a powerful cue for object association. However, they are often wielded as a one-size-fits-all hammer, applied uniformly across all videos through simple similarity metrics. We argue that this overlooks a fundamental truth: MOT is not a general retrieval problem, but a context-specific task of discriminating targets within a single video. To this end, we advocate for the adjustment of visual features based on the context specific to each video sequence for better adaptation. In this paper, we propose a history-aware feature transformation method that dynamically crafts a more discriminative subspace tailored to each video's unique sample distribution. Specifically, we treat the historical features of established trajectories as context and employ a tailored Fisher Linear Discriminant (FLD) to project the raw ReID features into a sequence-specific representation space. Extensive experiments demonstrate that our training-free method dramatically enhances the discriminative power of features from diverse ReID backbones, resulting in marked and consistent gains in tracking accuracy. Our findings provide compelling evidence that MOT inherently favors context-specific representation over the direct application of generic ReID features. We hope our work inspires the community to move beyond the naive application of ReID features and towards a deeper exploration of their purposeful customization for MOT. Our code will be released. The code is released at https://github.com/MCG-NJU/HATReID-MOT.
arXiv:2606.08015v2 Announce Type: replace
Abstract: We propose Q-Guided Value-Gradient Matching (Q-VGM), an off-policy reinforcement learning method for a central difficulty in fine-tuning flow-matching vision-language-action (VLA) policies: improving an expressive flow-matching action expert with a learned $Q$-function. Effective improvement must exploit the critic's first-order signal $\nabla_A Q$, yet flow policies make this hard: backpropagating values through the multi-step denoising chain is unstable at VLA scale, and the tractable action likelihoods required by policy gradients are unavailable under iterative denoising. Existing value-based methods therefore backpropagate through the full chain, use the critic only for test-time selection or guidance, or distill critic-improved actions as terminal labels that never supervise the velocity field. Q-VGM instead casts policy improvement as optimal control over the denoising dynamics, where the optimal residual velocity is the gradient of a denoising-time value function: clean-action estimates improved by iterative $Q$-gradient ascent with keep-best selection are converted into residual velocity targets that directly supervise the velocity field -- no action likelihoods, no backpropagation through the denoising chain, fully offline on a fixed replay buffer, and no critic at inference time. The critic is an action-sensitive stepwise IQL critic on compact latent states from the frozen VLA backbone. This enables a few-shot-initialization, learn-from-experience paradigm: starting from a few-shot-SFT $\pi_{0.5}$ policy, Q-VGM improves the policy from its own rollouts without additional expert supervision, raising the average LIBERO success rate from 79.0% to 92.5%, outperforming all same-backbone, same-critic baselines, and attaining high success rates on four real-robot manipulation tasks, including fine-grained plug insertion.
arXiv:2606.08723v3 Announce Type: replace
Abstract: Large Language Models (LLMs) are rapidly reshaping academic research across the natural sciences, social sciences, and humanities, yet the scientific community lacks a comprehensive, cross-disciplinary account of how these tools are being integrated, what they deliver, and where they fall short. This paper addresses that gap by mapping their current state and outlining an agenda for their responsible integration into scientific research. Our analysis reveals a consistent pattern: LLMs meaningfully accelerate research workflows -- from hypothesis generation and literature synthesis to data analysis and scientific writing -- while introducing serious challenges related to hallucination, reproducibility, dataset bias, and model opacity. Beyond technical limitations, we identify ten underexplored challenges, including the erosion of researcher autonomy, AI-driven confirmation bias, authorship ambiguity, and unequal access to these technologies -- systemic risks that demand interdisciplinary governance frameworks, robust validation standards, and expanded explainability research.
DECIS: Dual-Evidence Corrective Verification for Interpretable Strabismus Diagnostic Decision-Making
arXiv:2606.09249v2 Announce Type: replace
Abstract: Strabismus is a common ocular disorder that requires fine-grained subtype diagnosis for individualized treatment planning. However, existing deep learning methods mainly provide diagnostic predictions without transparent reasoning, while recent large vision-language models (LVLMs), although promising for joint image understanding and report generation, remain highly prone to hallucination in this evidence-sensitive and rule-driven medical task. To address these challenges, we propose DECIS, a Dual-Evidence Corrective verification for Interpretable Strabismus diagnostic decision-making framework. DECIS transforms black-box end-to-end generation into a structured diagnostic process consisting of candidate hypothesis generation, dual-evidence constrained context, evidence-based corrective verification, and report generation. Specifically, we introduce a Dual-Evidence Constrained Context (DECC) mechanism that jointly organizes visual evidence from the photograph of the nine cardinal positions of gaze and evidence-based clinical diagnostic rules into a constrained context for reliable diagnostic reasoning. We further develop an Evidence-Based Corrective Verification (EBCV) mechanism that verifies whether the current diagnostic hypothesis is supported by visual evidence, heatmap-based visual cues, and evidence-based clinical diagnostic rules. Hypothesis refinement is triggered when inconsistency is detected. Experiments on a fine-grained strabismus benchmark demonstrate that DECIS not only outperforms other state-of-the-art diagnostic systems, improving the weighted F1 score from 72.0% to 91.3%, but also improves the clinical reliability (consistency, alignment, and completeness) of generated diagnostic reports. These results demonstrate that DECIS provides an effective solution for building accurate, evidence-based, and clinically interpretable strabismus diagnosis systems.