Papers

Multi-agent pipelines that author formal documents must both read a requester's forms and write against them. We report a deployed tender-response system, running an open-weights model under sovereignty constraints, and evaluate it against human-written bids the same organisation actually submitted. On a blind comparison where the system had no worked example available, an LLM judge rated its answers at least as good as the human-submitted answer on $40$ of $55$ ground-truth sections, better on $4$, missing on none, and flagged one unsupported claim in total. Classifying every gap the judge identified shows that $68\%$ were content absent from the system's own sources – knowledge the human author held and the pipeline was never given – so only $6$ of the $15$ adverse verdicts involve a deficiency the system could have avoided. A divergence from ground truth is more often an information-availability result than a writing-quality one, and evaluations that do not separate the two understate such systems. Against this backdrop we report a conditioning asymmetry. It is well established that rendering documents as structural markup rather than flat prose improves extraction, and we reproduce that on three reading tasks. The benefit does not transfer to conditioning: converting a bid's instruction material from prose to nested XML dropped answer quality from $74\%$ to $48\%$ under a paired comparison. We further find that naming a forbidden construction concentrates rather than removes it – $96\%$ of surviving defects fall in the two forms the prompt explicitly names – and that coupling a stochastic annotation to a deterministic windowing function moves the extracted requirement count from $68$ to $51$ on a byte-identical file. Structure belongs where the model reads; prose and self-applied tests belong where it writes.

Imitation learning for robotics depends on human demonstrations, some of which people may later ask to remove. Retraining without them is the natural reference, but its cost grows with policy and dataset scale, motivating cheaper operators that edit a trained policy. Metrics inherited from machine unlearning, such as forgetting loss or a single membership attack, do not establish what an edit removed from a policy acting in closed loop. We therefore introduce a retrain-calibrated audit that reads demonstration unlearning along two axes: behavior, whether the edited policy acts like one retrained without the removed demonstrations, and evidence, whether an auditor can still detect it was trained on them. The behavior axis measures action divergence to that retrain at matched states, calibrated by a floor built from independent retrains, so a policy at the floor is as close to a retrain as retrains are to each other. The evidence axis applies a per-demonstration membership attack against a retrain null, reporting both its rank and its absolute member-loss level, since rank alone accepts operators that inflate member losses past the null. A conformal test then combines both axes into one hypothesis of joint retrain consistency, against a fleet of independent retrains large enough to reject at conventional significance. Across five preregistered conditions on three real-robot policy classes and two simulation suites, the axes dissociate in both directions on one checkpoint, as an edit may repair task behavior while leaving evidence unchanged, or reduce evidence while moving behavior away from retraining. On the ACT arm, a redirect edit restores blind-scored robot success to 18 of 20 trials.

Runtime assurance for autonomous systems increasingly requires reasoning not only about observed executions but also about anticipated future behaviors. Traditional runtime verification, however, primarily evaluates the execution observed so far and does not directly account for predicted continuations. We propose a formal framework for runtime assurance that combines monitoring of the observed execution with analysis of multiple predicted continuations. To support this integration, we introduce Split Linear Temporal Logic (SplitLTL), a linear-time temporal logic that assigns complementary roles to past and future temporal specifications within a single specification. The past component uses the observed history to determine the assurance requirements applicable at the current point of execution, while the future component evaluates predicted continuations against those requirements. The framework therefore filters predicted continuations according to the requirements induced by the observed history, identifying admissible continuations that can support subsequent decision making. We formally define the syntax and semantics of SplitLTL and present an online monitoring architecture for evaluating observed executions together with predicted continuations.

As scientific literature grows and papers increasingly under-report limitations, multi-agent LLMs offer a promising approach to systematically uncover these hidden failure modes. Here, we introduce Tree-of-Concerns, a multi-agent framework that deploys specialized skeptic personas, each operating through a category-specific analytical lens, as parallel debate trees to extract unstated limitations from scientific papers. Each persona conducts structured, evidence-grounded argumentation, while a Panel Review mechanism re-evaluates each surviving claim from all five perspectives to correct category drift and severity miscalibration. Through retrieval-free, single-paper experiments on ToC-Bench, our benchmark of 414 research papers with 1,905 unstated limitations, sourced from reviewer-reported weaknesses and follow-up citation critiques, we demonstrate that ToC improves precision by 79% and coverage by 11% relative to the strongest baseline, surfacing specific, evidence-grounded concerns that support reviewers in systematic evaluation.

Automated code translation is increasingly important for software evolution, yet the relative strengths and limitations of learning-based and large language model (LLM)-based techniques remain insufficiently understood. To address this gap, we conduct a large-scale empirical study comparing representative code translation techniques across methodological paradigms and translation granularities. We evaluate learning-based methods, LLM-based methods, and general-purpose LLMs on multilingual method-level and class-level benchmarks involving multiple programming languages. Our analysis considers executable correctness, code similarity, translation direction, translation granularity, and failure patterns. The results show that LLMs and LLM-based methods generally outperform learning-based methods in method-level correctness, although similarity metrics alone do not reliably reflect functional correctness. Translation direction substantially affects performance, particularly when translating between languages with different type-system characteristics. Class-level translation remains considerably more difficult than method-level translation because it requires preserving global semantics, interfaces, member relationships, and cross-method dependencies. Our error analysis further shows that static semantic errors and logical errors are the primary challenges in existing code translation systems. These findings provide empirical evidence and practical guidance for developing more robust, type-aware, structure-aware, and context-aware code translation techniques.

Search Agents face a severe reliability crisis during reinforcement learning (RL) fine-tuning. Heuristic Top-K retrieval often causes critical evidence loss or noise inclusion, while over-confidence induced by progressive RL leads to hallucinated answers and redundant searches. To build highly reliable agents, we introduce Conformal Prediction (CP) and propose Conformalized Agentic Search (CAS). This framework establishes reliability guarantees on both the retrieval and training sides: on the retrieval side, an Adaptive Prediction Set (APS), a specific CP realization, translates statistical coverage into dynamic document truncation to construct prediction sets that are adaptive in size; on the training side, Adaptive Conformal Inference (ACI), a dynamic CP algorithm, dynamically constructs prediction sets with controllable coverage to quantify answer confidence, which is then used to penalize low-confidence trajectories within the Group Relative Policy Optimization (GRPO) objective, ensuring the model learns only from reliable ones. Experiments across single-hop and multi-hop QA datasets demonstrate that our framework significantly improves reasoning accuracy while drastically reducing redundant tool invocations, establishing a highly reliable and efficient agent paradigm. Our code is available at https://github.com/S1llyBird/CAS.

Modern AI video generation models can produce videos with high visual fidelity and seemingly smooth temporal transitions. However, visual realism does not necessarily imply physical motion consistency. Existing generative models mainly optimize distribution matching in pixel or latent spaces, without explicitly enforcing real-world constraints such as inertia, continuous forces, and trajectory geometry. Our experiments show that AI-generated videos remain visually plausible over short sequences of consecutive frames, yet fail to preserve physical motion consistency throughout a complete object action, resulting in systematic statistical discrepancies in their motion trajectories. Based on this observation, we introduce MotionPhys, a lightweight and interpretable framework that treats sparse motion trajectories as physical evidence rather than relying on appearance artifacts or generator-specific traces. By modeling the geometric evolution of trajectories across multiple temporal scales, MotionPhys reveals subtle motion inconsistencies that are difficult to capture with conventional visual cues and transforms them into a compact representation for efficient detection. Experiments on multiple datasets show that MotionPhys can effectively detect physical inconsistencies in generated videos and generalizes well across different video generators.

Streaming emotion understanding uses historical state while continuously interpreting current audio, often feeding the model's previous prediction back as context. We show that this history conditioning can distort current perception. On a balanced CREMA-D-Stream counterfactual diagnostic, changing only the injected previous emotion label while holding the audio fixed reduces current-audio accuracy from 72.50% to 30.42% and flips 65.69% of predictions. The effect is strongly label-asymmetric, with prior pull ranging from 4.76% to 98.20%, revealing a failure we call previous-belief contamination (PBC). To address PBC, we introduce EmoUpdate, a training-free framework that separates current-audio perception from historical state revision through three components: (1) a prior-blind acoustic firewall that prevents historical state from entering perception; (2) an evidence-shrunk causal belief filter that introduces history only after observation formation and retains label-asymmetric transition structure only when supported by observed evidence; and (3) a closed-form decontamination operator derived from the same counterfactual measurements for serving stacks where firewalling is unavailable. Across four SpeechLMs and two streaming emotion benchmarks, EmoUpdate achieves the best step accuracy and state-balanced accuracy in all eight model–benchmark settings, improving S-BAcc by up to 69.71 points and step accuracy by up to 38.41 points over the strongest controlled baselines.

Specialist language models are usually understood through endpoint gains: the generalist scores lower, the specialist scores higher, and the difference is treated as evidence of specialization. This leaves the released update itself largely unexamined. We propose a paired weight-delta path audit and apply it to two public, aligned generalist-to-medical-specialist checkpoint pairs: Gemma-3-4B-IT to MedGemma-4B-IT and Qwen2.5-7B-Instruct to HuatuoGPT-o1-7B. In both pairs, the full decoder-side update strongly reconstructs measured medical benchmark movement (0.974 and 1.183 endpoint-normalized retention), making each decoder delta an appropriate substrate for the audit. Yet the movement is not cleanly localized. MLP is the strongest broad component family in both pairs, but mixed off-domain movements, 10-seed matched controls, and endpoint-anchored rollbacks prevent a unique coarse-family explanation. The audit therefore separates update-level reconstruction from component-level explanation. Its claims concern text-only multiple-choice benchmark movement, not clinical validation, repair, or circuit-level mechanism.

Bipartite graphs are a fundamental representation for relational data arising in recommendation systems, social networks, and communication graphs. A key challenge in these settings is to store and transmit large bipartite graphs compactly while preserving exact structural and path information. We study biclique-based representations of bipartite graphs $\boldsymbol{G}=(\boldsymbol{V},\boldsymbol{U},\boldsymbol{E})$, where the edge set is encoded using a collection of complete bipartite subgraphs. We focus on the Weighted Biclique Covering problem, which minimizes the total number of vertices used across all bicliques, and introduce a generalized variant that additionally penalizes the number of bicliques, capturing practical overheads in storage, transmission, and model complexity. While the weighted biclique covering problem is known to be $\mathsf{NP}$-Complete, we show that the generalized variant is also $\mathsf{NP}$-Complete. Despite this hardness, many real-world bipartite graphs admit low-dimensional geometric embeddings or can be well approximated by them. Leveraging this observation, we develop the first approximation algorithms with provable guarantees for the (generalized) weighted biclique covering problem on geometric bipartite graphs. Specifically, for $\delta$-disk bipartite graphs in low-dimensional $\ell_\infty^d$ spaces, we design a polynomial-time algorithm that achieves an $O(\log |\boldsymbol{U}| \cdot \log^d |\boldsymbol{V}|)$-approximation, combining ideas from greedy set cover, geometric range searching, and densest subgraph optimization. We also show how our algorithms extend to $\ell_\alpha^d$ metrics for any $\alpha\geq 1$. Finally, we evaluate our algorithms on real-world bipartite datasets and show that they efficiently compute significantly smaller biclique-based representations than natural baselines, while scaling to large graphs.

As an extension of existing Bayesian persuasion framework with inadequate message mechanism, we study direct recommendation when a sender is bound by an installed information policy only with probability $\rho$, the realization of binding is hidden, and the receiver does not observe the persistent structural environment. The receiver first sees a payoff-neutral, nonmanipulable calibration sample and then faces a fresh, non-certified deployment interaction. In common, the calibration law identifies only the receiver-facing reduced form, not the latent binding and discretionary kernels. We characterize type-wise $\rho$-implementability, construct the receiver's posterior over the full deployment node, and prove a static direct-following implementation theorem. After every calibration history that passes a posterior-predictive obedience test, the deployment assessment is an exact perfect Bayesian equilibrium: Bayes consistency, receiver sequential rationality, sender sequential rationality, and off-path completion are all verified. Under finite-type separation, common recommendation support, and a positive obedience margin, the test activates such an equilibrium with high probability. Our results keep statistical failure probability distinct from equilibrium approximation. Finally, we embed the original robust value frontier, support-wise linear-programming algorithm, and binary-action fractional-knapsack specialization into this implementation framework

Linear probes and activation steering have uncovered that vision-language models (VLMs) internally represent mental states such as agents' beliefs, knowledge, and intentions. However, it is unclear whether and how these representations are used by downstream predictions along these axes. To close this gap, we introduce Cross-Axis Routing Diagnostic (CARD), which steers activations along one axis while measuring the response of a different axis's prediction. Applied to open-weight VLMs on Relay Chain – a new cooperative grid-world benchmark we propose – we diagnose a critical routing failure: models fail to incorporate belief representations into their next action prediction, effectively leaving valuable information about their partners unused.

In non-stationary multivariate time series, different variables and samples often exhibit heterogeneous latent dynamic states, while existing deep forecasting models usually compress them into a unified end-to-end mapping, leading to suboptimal modeling of time-varying dynamics and limited interpretability regarding which forecasting mechanism is activated under different latent states. To overcome these limitations, we reformulate time series forecasting as a unified framework of latent temporal state identification and interpretable expert routing, and propose Fuzzy-MoE, a fuzzy logic-based dynamic Mixture-of-Experts model. Fuzzy-MoE consists of multiple parallel expert mapping networks and a dual-view fuzzy router. By jointly exploiting local convolutional dynamics and global segmented statistics, the router infers latent temporal states and computes expert activation strengths through learnable Gaussian membership functions, enabling explicit IF-THEN rule-based expert selection. This fine-grained routing strategy allows different variables within the same sequence to activate different experts, effectively capturing heterogeneous temporal dynamics while improving model interpretability. Experimental results on multiple public time series benchmark datasets show that Fuzzy-MoE significantly outperforms mainstream forecasting methods in forecasting accuracy. Moreover, fuzzy memberships and rule activations provide interpretable routing diagnostics, demonstrating the effectiveness of the proposed framework in both forecasting performance and mechanism transparency. Unlike traditional MoE models that use black-box routing, Fuzzy-MoE`s routing is based on clear, interpretable fuzzy rules. This makes the expert selection transparent and traceable.

Single-image 3D human reconstruction often suffers from over-smoothed textures and geometric inconsistencies. While diffusion models improve generative quality, their reliance on multi-view synthesis prior to 3D reconstruction is computationally expensive and prone to view inconsistency. We propose DiGS-Avatar, which reformulates this task as an efficient, diffusion-based UV-latent completion task, ensuring 3D consistency by design. To capture accurate spatial structure, we introduce a teacher-student framework where a multi-view teacher provides geometrically aligned pseudo-ground-truth latents to supervise a single-view diffusion student. Treating this inferred latent as a robust structural skeleton, our method injects high-level semantic features to accurately recover fine textural details without disrupting spatial integrity. The refined representation is then decoded into 3D Gaussian primitives. Extensive experiments demonstrate that DiGS-Avatar achieves state-of-the-art or highly competitive visual fidelity and zero-shot generalization, while reconstructing a fully animatable 3D avatar in just 0.71 seconds. Code is available at https://github.com/KLMAV-CUC/DiGS-Avatar.

Bayesian Neural Networks (BNNs) with Bayesian output layers provide a principled and tractable framework for quantifying predictive uncertainty, yet the mechanisms shaping that uncertainty remain unclear. While conventional theory attributes uncertainty reduction to posterior contraction, the corresponding assumptions need not hold for deep models. In the Graph Neural Networks (GNNs) with Bayesian output layers studied here, we observe that predictive uncertainty decreases as latent representations shift toward lower-variance posterior directions, even though the posterior variance does not contract. We term this behavior Latent-Posterior Alignment (LPA) and conduct interventional experiments that support its functional role in shaping predictive uncertainty. Building on this insight, we propose Alignment-Guided Learning (AGL), which explicitly promotes this alignment during training. AGL effectively reduces predictive uncertainty while preserving accuracy and improves structural calibration, ensuring that the model confidence faithfully mirrors underlying data density. These findings provide a new perspective on uncertainty dynamics in GNNs with mean-field Bayesian output layers, shifting the focus from the magnitude of the posterior to the geometric interplay between latent and parameter spaces.

We describe the PSK submission to the WMT 2026 Multilingual Instruction Shared Task. Our system uses the 3.35B-parameter Tiny Aya Global model with three QLoRA adapters, one for each task. The adapters are trained on multilingual document-summary pairs, passage-based question answering, and filtered standalone question answering. The summarization data also includes scientific papers with their author-written abstracts. On our held-out split, the context and summarization adapters perform better than our multitask adapter, which was trained only on data supplied by the organizers. Results for open QA are mixed and vary with answer length and evaluation method. We therefore submit three systems with the same context and summarization adapters but different open-QA adapters.

While multimodal retrieval-augmented generation (RAG) systems increasingly rely on images as external knowledge sources, the introduction of poisoned visual evidence can severely compromise multimodal large language model (MLLM) generation. Unlike prior attacks that rely on altering textual metadata, we introduce Vis-Poison, a novel visual knowledge poisoning attack where the poisoned image itself is the attacker-controlled payload, without manipulating captions, summaries, metadata, or other associated text. Specifically, this attack is instantiated through an automated multi-agent method that constructs visually plausible poisoned images. To assess its impact, we evaluate Vis-Poison across two representative multimodal RAG pipelines, four embedding models, and six generation models. Empirically, Vis-Poison achieves an end-to-end attack success rate of 40.16% to 65.40% against 30k-entry multimodal knowledge bases in black-box settings. Moreover, Vis-Poison remains effective against various MLLMs that can answer correctly from parametric knowledge alone, with an average success rate above 60%. Code and data are available at https://github.com/SWUFE-DB-Group/Vis-Poison.

Modern de novo design workflows generate many candidate protein binders, but wet-lab validation capacity remains limited, making shortlisting a major bottleneck. We study whether LLMs can generate multi-metric ranking policies from precomputed structural-confidence and interface-quality proxy scores. Rather than proposing a new protein binder design pipeline, we focus on post-generation binder shortlisting: selecting the final top-K candidates from already generated binder pools using a shared panel of precomputed proxy scores. On the 10-target held-out split, averaging performance over five sampled global iterative gpt-4o policies reaches 0.589 Recall@10, modestly improving over the strongest single-feature fixed baseline, Protenix binder ipTM, which reaches 0.571 Recall@10. On the 3-target held-out subset comprising Nipah, RBX1, and TREM2, target-conditioned iterative gpt-5.4 policies reach the strongest LLM performance, with 0.519 Recall@10 and 0.583 NDCG@10. These results suggest that LLM-generated ranking policies can act as an interpretable post-generation decision layer for combining heterogeneous proxy metrics to prioritize binders from large candidate pools.

Promptable segmentation models provide a reusable interface, but direct transfer to automatic infrared small-target segmentation (IRSTD) exposes a mismatch between spatial prompts and target-domain mask responses. In a diagnostic using target-covering loose-box prompts deterministically derived from test reference masks, the best official SAM2.1 results are only 4.69%, 1.64%, and 2.28% IoU on NUAA-SIRST, NUDT-SIRST, and IRSTD-1K. We introduce SPARK-SAM (Self-Prompt Adaptation with Response Knowledge for SAM), which learns target-domain response knowledge and conditions the decoder through an image-conditioned joint self-prompt state. Training combines benchmark-mask supervision with reliability-aware response guidance. SPARK-SAM achieves 75.78%, 86.49%, and 68.34% IoU with 0.726M additional parameters, ranking first on two benchmarks among 14 retrained SAM variants and adaptations evaluated as automatic image-to-mask methods. The staged IRSTD-1K diagnostic shows that response adaptation reaches most of the final IoU before the predicted points acquire reliable target grounding. Prompt supervision aligns the predicted prompt candidates with target locations, and frozen-weight interventions measure output sensitivity to the joint self-prompt state. Matched ablations show consistent accuracy gains from response guidance and high-resolution prompt refinement across all three datasets. Code is available at https://github.com/Sakauma/SPARK-SAM.

Knowledge of the nautical rules of the road is essential for safe ship navigation and collision avoidance. We evaluated adaptive and non-adaptive versions of a ship-driving simulation trainer designed to assess and improve students' knowledge and application of these rules. We randomly assigned 30 university students to an adaptive or non-adaptive training condition and measured learning using pretest and post-test scores. Students who received adaptive training achieved significantly higher post-test scores than those who received non-adaptive training (p < 0.0001). After the post-test, all students experienced both versions of the trainer and compared them in a survey. Of the 30 students, 73% judged the adaptive trainer more effective, and 22 rated it "very engaging," compared with 9 who gave the non-adaptive trainer the same rating. These findings provide evidence that adapting scenario difficulty and providing immediate, context-sensitive feedback can improve both learning outcomes and student engagement in simulation-based training.

Identity-preserving video generation aims to synthesize videos that follow natural-language instructions while maintaining the visual identity of a given subject. Recent commercial video generation models have achieved strong visual quality and motion realism, but they still suffer from identity drift, incomplete instruction following, and missing visual details under complex prompts. Since these models are usually closed-source black boxes, directly improving them through parameter optimization is often infeasible. We therefore propose Agentic Enhancement and Semantic Repair (AESR), a lightweight enhancement framework for identity-preserving video generation. To improve prompt construction before generation and mitigate the above failures, AESR introduces a global agentic prompt enhancement module. This module learns model-specific prompting formats from official documentation, acquires human-centered video generation priors from human-interaction data, and accumulates test-domain identity-preserving generation experience into a reusable playbook through an agentic loop. To further repair errors in videos generated with enhanced prompts, AESR introduces a sample-level visual semantic repair module, which uses a VLM to locate erroneous video segments and design repair instructions, edits selected frames into explicit visual references, and guides a video editing model to fix local semantic or identity-related errors. We also adopt a lightweight Mixture-of-Experts selection strategy to choose reliable outputs from different generation and refinement paths. Under the official evaluation protocol of the ACM MM 2026 Identity-Preserving Video Generation Challenge, our system MIPL\_Video ranked first in Track 1, demonstrating the effectiveness of AESR for practical identity-preserving video generation. The code is available at https://github.com/oceanflowlab/AESR.

The Visual Geometry Grounded Transformer (VGGT) enables unified feed-forward 3D reconstruction from multi-view images. However, deploying such a high-performance model may expose critical security vulnerabilities. Traditional adversarial perturbations require costly per-scene optimization, while Universal Adversarial Perturbations (UAPs) rely on a single static pattern and fail to effectively attack VGGT. To address these limitations, we propose MVAP-G, a multi-view adversarial perturbation generator that produces imperceptible consistent perturbations across multiple views in a single feed-forward pass. To ensure perturbation consistency across diverse scenes, we design a cross-view adversarial alignment mechanism to process multi-view images. Experiments demonstrate that MVAP-G significantly degrades VGGT performance without iterative optimization during inference. This work pioneers multi-view adversarial attacks on 3D foundation models, uncovering severe vulnerabilities and underscoring the urgent need for robust 3D vision systems. The code is available at https://github.com/qsong2001/mvap-g.

Speculative decoding accelerates autoregressive generation by allowing a lightweight drafter to propose future tokens while a target model verifies them in parallel. Its lossless guarantee has motivated a line of work that pushes the drafter itself toward parallel generation. The most recent paradigm is block-parallel generative drafting, including diffusion-based methods such as DFlash and DSpark, achieving up to 3.6x speedup on common daily chatting tasks. While this transition is well studied in text-only LLMs, its applicability to multimodal models remains an open question. Existing multimodal speculative decoding efforts focus on input compression, adapter alignment, candidate coverage, or modality-specific verification; however, block-parallel generative drafting remains largely unexplored. To bridge this gap, this paper combines a modality-centered survey with a cross-architecture empirical study to ask: Is multimodal speculative decoding ready for diffusion-based parallel drafting? In this survey, we systematically analyze a wide spectrum of multimodal models, spanning Vision-Language, Video-Language, Audio, and Vision-Language-Action (VLA) architectures, from the dual perspectives of drafting parallelism and cross-modal information interaction. We introduce a unified taxonomy that isolates drafter-side parallelism from orthogonal design choices such as tree construction and verification strategies. Furthermore, we provide a comprehensive empirical comparison of existing methods under varying degrees of parallelism across standardized multimodal benchmarks, including OCR, VQA, visual reasoning, and image captioning. Finally, we summarize the limitations of current approaches, discuss open challenges, and outline promising future directions for this rapidly evolving field.

State-of-the-art 3D reconstruction models, whether from visual, range, or both, tend to underperform on thin objects. This is partially due to the small amount of space such objects occupy in RGB images and in 3D point clouds. To test the extent of their errors, we collected the first thin object dataset comprising of synchronized RGB images, depth maps, and tactile response maps, where each frame is associated with inertial measurements, camera pose and calibration, and groundtruth depth and segmentation maps obtained from laser scanning of thin objects. We hypothesize that tactile data can aid in the reconstruction of thin objects as their response maps provide local shape and deformation information. Our dataset, termed VisTa3D, comprises of 387 scenes covering 70 thin objects over 17 environments. We benchmarked current 3D reconstruction models on VisTa3D and found that, indeed, they exhibit low fidelity on thin objects. To test if tactile data can help, we introduce the first visual-range-tactile 3D reconstruction model as a baseline. Code and data: https://huggingface.co/datasets/shaniaguo/VisTa3D.

The trace of the average mixing matrix of a quantum walk measures the "laziness" of the walk: the higher the trace, the more likely that the walker returns home in the long run. In this paper, we develop tools to study this graph invariant arising from Laplacian quantum walks. It is known that the complete graph $K_n$ is the laziest connected graph on $n$ vertices. Using our machinery, we show that the star $S_n$ is the second laziest connected graph on $n$ vertices (and hence the laziest tree on $n$ vertices), the complete multipartite graph $K_{n-2,1,1}$ is the third laziest connected graph on $n$ vertices, and the double star $DS(n-3,1)$ is the second laziest tree on $n$ vertices. We also show that on the same number of vertices, more unbalanced double stars are lazier.

Graph Neural Networks (GNNs) are widely used on graph-structured data, but most suffer from two key weaknesses. First, message passing behaves as a low-pass filter under the homophily assumption, leading to poor performance on heterophilic graphs. Second, stacking layers drives node features toward constants, causing over-smoothing. Existing methods usually address these issues separately, while the few joint solutions rely largely on empirical heuristics, and many over-smoothing remedies sacrifice model expressiveness. We propose CTQW-GNN, a GNN based on Continuous-Time Quantum Walks (CTQW), to address both issues with theoretical justification. Its design exploits two properties of the CTQW propagator $e^{-\mathrm{i}Ht}$. First, it is unitary and has eigenvalues on the unit circle, so no frequency component is damped, counteracting the low-pass bias. Second, unitarity preserves feature norms and prevents the Dirichlet energy from decaying exponentially with depth, thereby mitigating over-smoothing. CTQW-GNN combines three complementary aggregation modules. CTQW-based Aggregation evolves node features through the unitary propagator, preserving mid- and high-frequency signals for heterophilic graphs while preventing Dirichlet-energy collapse. CTQW-Attention Aggregation constructs a multi-hop neighbor graph from CTQW amplitudes and applies attention over it, enabling access to distant homophilic nodes missed by single-hop aggregation. LF Aggregation uses a standard low-pass GAT branch to retain strong performance on homophilic graphs, where pure CTQW aggregation can be suboptimal. We further provide a spectral-gap analysis explaining energy preservation and a Lieb–Robinson-type bound that gives a principled rule for selecting the walk time $t$.

Manipulating moving objects requires a policy to anticipate contact events, yet vision-language-action (VLA) policies are commonly fine-tuned from the current observation alone. World action models (WAMs) learn predictive dynamics, but running a video-scale teacher or explicitly imagining future frames at deployment is costly. We introduce ForeTime-VLA, a dense pi0.5 policy that distills a future-aware, action-equivalent representation from a frozen Fast-WAM-derived teacher while remaining causal at inference. Offline, current and future video latents are compressed into a whitened 64-D target. Online, an eight-frame history encoder predicts this target together with manipulation phase and normalized time-to-transition. Four future tokens and one phase token condition the VLM prefix, while the predicted future and transition horizon condition the action expert. Training retains the original flow-matching action target and adds cosine, relational geometry, phase, time-to-transition, and action-equivalence objectives. On a deduplicated conveyor-belt dataset, we compare 40k-step checkpoints on 768 matched windows per split. Test MAE decreases from 0.134119 to 0.130593 (2.63%; paired-bootstrap 95% CI: 0.82-4.48% improvement), and test L2 decreases by 3.02%, at a 2.46-2.93% latency cost. In quantitative real-robot evaluation, ForeTime-VLA achieves 81.1% stationary and 58.9% slow-moving grasp success, exceeding the next-best reference by 12.2 and 22.2 percentage points, respectively. Across three belt speeds, it completes 44/90 grasps versus 23/90 for pi0.5, including 11/30 versus 2/30 at fast speed. The agreement between offline orientation gains and reduced real-robot contact-pose failures supports causal future-token distillation as an effective way to improve dynamic manipulation without deploying the world-model teacher.

Managing the energy consumption and power efficiency of parallel applications is a significant issue in both HPC environments and in the cloud. As emerging applications continue to push against the memory wall of modern machines, the growing imbalance between compute and data movement creates new opportunities to intelligently tune CPU power consumption. Unfortunately, existing frequency and voltage scaling techniques do not adequately capture fine-grained changes in memory access behavior, rendering the compute/data access imbalance invisible to the components of the system that could capitalize on it, thus leaving potential power savings on the table. In this paper, we propose MEMPOWER, a flexible, model-based approach to exposing compute/data movement imbalance that characterizes the fine-grained memory behavior of parallel workloads. This characterization then informs our automated software framework which can statically instrument the application binary with model-determined voltage/frequency transitions that balance fine-grained changes in memory access behavior with the costs of hardware transitions. Using MEMPOWER, we demonstrate a reduction in EDP of 6% to 42% on a range of HPC benchmarks with minimal impact on execution time when compared to the standard OS/hardware-managed power control mechanism.

LLM API resellers have become an important access layer to modern LLM services. However, multi-level resale creates an opaque supply chain: a user's request may traverse undisclosed upstream resellers, each of which can inspect or modify prompts and responses, inducing ecosystem-level confidentiality and integrity risks. Existing studies audit individual resellers, but provide little visibility into hidden dependencies across resellers. We present CacheTracer, the first API-only measurement of such hidden dependencies. Our key insight is to exploit prefix-cache reuse as a side channel to measure dependency via cache-reach relations. CacheTracer operationalizes this insight with two primitives: Flood populates fresh cache state through one endpoint, and Prove probes whether another can reuse it while excluding probe-created hits. We then conduct a real-world measurement study with CacheTracer on 39 reseller endpoints, sending 1.1 million API requests across 636 endpoint pairs. Our measurements reveal a deep, concentrated cache-reach structure: 37.1% of measured pairs exhibit shared cache reach, the containment order spans seven layers, and one cache reach is contained within at least 31 of other nodes. We further find that the recovered structure is model-specific. We also evaluate the validity of CacheTracer through both real-world consistency checks and controlled experiments. The results show its high reliability and accuracy. These findings reveal substantial hidden dependencies among seemingly independent API resellers. Such deep and concentrated dependencies can create a large potential blast radius, where a confidentiality or integrity failure along a common upstream path may affect users across multiple downstream resellers.

Language-model agents can improve after failure or carry text across episodes without revising what counts as success. We study the narrower attribution problem of criterion revision: when criterion K0 accepts an outcome violating a broader commitment B, what observations justify saying that the system formed and persistently used K1? We require five non-compensatory conditions: criterion-failure detection, a model-emitted proposal, new-episode transfer, intervention sensitivity on the claimed carrier, and preservation. We evaluate CMB-0.1 on twelve cross-domain cases and four arms: stateless inference, append-only history, model-generated but harness-committed state, and evaluator-written oracle state. Seven mechanism fixtures yield 84 deterministic scorer trials; four local quantized artifacts yield 96 calls and 192 model-case-arm trials. No model trial satisfies all five conditions, but this zero does not establish general capability absence. Eleven calls remain invalid after one retry; several commitments disclose the target distinction; the harness performs commits; deletion reuses a stateless call; and conflict changes multiple factors. Qwen2.5-7B answers every transfer and preservation item without revision state, exposing zero-state reconstruction. These failures make CMB-0.1 an instrument-calibration result rather than a model ranking. We derive a prospective, trace-anchored CMB-0.4 protocol requiring concealed transfer, explicit WRITE/NO-WRITE/ESCALATE actions, a separately logged policy-selected commit, matched interventions, repeated hidden items, and a frozen executable oracle. It is a successor design, not a completed confirmatory result. The paper contributes a measurement chain, an empirical diagnosis of its first implementation, and a more discriminating protocol for future tests of criterion revision.