Papers

Although uniform diffusion language models (UDLMs) represent a promising diffusion paradigm, scaling them remains challenging. We identify the core obstacle as an over-uniform training objective and condition-target confusion during sampling. To address these, we propose Less Uniform Diffusion (LUDI), a novel UDLM framework. Specifically, we (i) introduce a less uniform loss that directs each reverse transition toward the clean token, and (ii) equip the model with per-token time embeddings that supply token-level corruption hints, enabling confidence-based few-step sampling. Experiments across scales show that LUDI yields cleaner supervision and improves few-step generation. We further continue-train a 7B autoregressive model into LUDI-7B, resulting in a UDLM capable of complex reasoning. It achieves a 3-token-per-step speedup over AR decoding and competitive performance compared with masked diffusion baselines, revealing that the full potential of UDLMs for complex generation remains to be unlocked.

Transferring deformation between characters with different geometry and topology is challenging because conventional rigs encode behaviour through character-specific structures and correspondences. We present LatentReRig, an experimental framework that investigates whether pose-associated changes can instead be represented as reusable directions in a learned geometric latent space. An SDF-based variational autoencoder is coupled with two decoders: one reconstructs the implicit field, while the other predicts target vertex positions from source geometry and latent deformation conditioning. The source geometry may be neutral or already deformed. Experiments on a controlled humanoid dataset show that several poses induce coherent latent directions across identities, particularly for broad articulated motions. These signals can guide deformation of unseen characters, but explicit predictions remain less accurate for localized changes and corrective contributions. Diagnostic comparisons with repeated SDF sampling show that inter-identity distances exceed same-geometry resampling variability on average, while pose signals exhibit different margins above this baseline. The results support the presence of reusable pose-related structure and identify stable local conditioning and accurate mesh decoding as complementary requirements for improving transfer.

Evaluating conversational systems is a difficult and unresolved problem. We introduce the Conversational Distribution Score (CDS), which compares distributions of conversational behaviour using human conversations as a reference. CDS describes speech rate, syllabic rhythm, and turn interaction through eight interpretable features plus a separate two-feature semantic baseline. We compare conversations with two reference scales: one based on conversational success within human dialogue and another contrasting human and synthetic dialogue. Using listener judgments from out-of-domain goal–oriented dialogues, we examine system ranking, preferences between conversations, and ranking stability. Composite CDS recovers five of six listener system comparisons while individual features show strong correlation with listener preferences between conversations. We examine how many minutes and conversations are required before rankings stabilize. These findings support distributional comparisons as a complement to specific interactional metrics to evaluate conversations and conversational models while showing their interpretable value.

Images often carry recommendation constraints that text metadata only hints at. A movie may need to look dark, a product may need a minimal style, and a visually impossible request should be rejected. Agentic multimodal recommenders must reason over text-image evidence, decide when visual evidence is decisive, and abstain when no valid action exists. We introduce MM-VeriRec, a verifiable multimodal recommendation protocol and failure-guided fusion method for hidden visual constraints, image-text mismatch, and impossible-task abstention. MM-VeriRec builds tasks from real movie-poster and product-image datasets, verifies each recommendation with deterministic visual attributes, and converts failures into actionable labels: text-trap following, visual ignorance, and false acceptance. Fusion should not merely concatenate modalities, but should diagnose which modality failed and route to the appropriate repair. Across MM-ML 1M and Amazon Reviews datasets, stronger text and vision embeddings improve retrieval but do not remove these failure modes, whereas failure-guided fusion does. The adaptive attribute gate reads the same tags the verifier checks and its scores are verifier-aligned upper bounds testing whether the taxonomy routes to the correct repair. More informative is transfer under a non-aligned gate: an independently derived leave-one-out CLIP detector still reaches 0.7028 and 0.6111 visual-grounded success, above both a VBPR baseline and plain fusion. The text-versus-visual gap reproduces across two LLM families, and the repair that helps differs by domain. MM-VeriRec is both a benchmark and a practical diagnostic loop for trustworthy agentic multimodal recommendation.

Vision-Language-Action (VLA) policies have shown promising performance in language-conditioned robotic manipulation. However, most existing VLA systems rely on conventional perspective cameras with limited fields of view, often missing global scene context and leading to unreliable manipulation under visual occlusions, distractors, and unseen environments. In this work, we propose PanoFuse, a panorama-enhanced VLA framework that complements local manipulation observations with global panoramic perception. PanoFuse introduces a dedicated panoramic branch that leverages a pretrained panoramic foundation model to extract complementary semantic and geometric representations from omnidirectional observations. Rather than directly mixing these heterogeneous features, we introduce Decoupled Semantic-Geometric Routing (DSGR), which maintains semantic and geometric representations as separate context streams and selectively routes both to downstream state and action representations through structured block-wise attention. This design provides the action expert with global spatial context while preserving task-relevant semantic information from the pretrained VLA backbone. We further develop a synchronized data collection pipeline and construct a new real-world manipulation dataset containing panoramic RGB observations, wrist-view images, language instructions, robot states, and actions. Across seven evaluation settings, PanoFuse achieves an average success rate of 52.9%, outperforming the evaluated baselines and achieving consistent gains under novel-object, unseen-background, and distractor-rich settings. Code and data will be released publicly at https://xux-hnu.github.io/PanoFuse.

Persistent semantic occupancy mapping is essential for embodied scene understanding. However, perspective-based systems provide limited spatial coverage, while existing panoramic methods primarily predict local volumes from single observations. We introduce PanOVOcc, a training-free framework for persistent open-vocabulary semantic occupancy mapping from panoramic sequences. PanOVOcc unifies panoramic SLAM, open-vocabulary perception, and long-term spatial voxel memory within an online architecture, continuously integrating geometric and semantic evidence into a global, language-queryable map. To facilitate systematic evaluation of this setting, we establish Pan-Replica and Pan-Holo360D, two benchmarks pairing continuous panoramic RGB-D sequences with scene-level semantic occupancy ground truth across synthetic and real-world scenes. Compared with the strongest evaluated baseline for each metric, PanOVOcc improves occupancy IoU and semantic mIoU by absolute +20.03 and +7.06 on Pan-Replica, and by +43.26 and +20.16 on Pan-Holo360D, respectively. The source code and the established benchmarks will be available at https://github.com/bakereet/PanOVOcc.

Agentic recognition requires visual perception to move beyond static scene understanding and produce structured scene representations that support the perception–reasoning–action loop. Existing single-image 3D generation methods, however, mainly produce visually plausible object assets rather than simulation-ready scene states. When independently generated meshes are composed in a shared space, they may fail to align with the input camera, violate gravity, interpenetrate nearby objects, or become unstable under physics simulation. We present Fysiverse-3D-SimReady, a grounded refinement framework for reconstructing simulation-ready multi-object scenes from a single RGB image with instance and ground prompts. The method places generated object meshes into a shared gravity-aligned scene, refines their camera-space poses through differentiable rendering, and corrects scene-level supports and contacts for stable physical execution. The scene is then used by an agentic simulation workflow, which converts a scene-specific task goal into an executable physics rollout rendered from the original camera view. Experiments show that Fysiverse-3D-SimReady improves input-view alignment, contact plausibility, and physical stability over existing single-image reconstruction and scene generation baselines, while enabling goal-conditioned physical interactions from a single image.

Building omni-modal models with physical intelligence requires fine-grained supervision that captures physical evidence such as contact, support, deformation, and state transitions. However, existing omni-modal captioners primarily model general audiovisual semantics and often overlook transient or spatially localized physical evidence. We present a unified framework for physics-aware audiovisual captioning spanning data construction, training, and evaluation. Firstly, we build a data construction pipeline that identifies physics-rich clips and leverages OmniFysics-Agent to coordinate audio, visual, and physical-perception tools for collecting spatiotemporally aligned and traceable cross-modal evidence; within the Agent, a physical perception model (PPM) fine-tuned on approximately 2M image-level samples serves as a dedicated tool for extracting object-interaction and state-change cues. Secondly, we build the Daily-Physics 50K dataset and introduce the evidence-driven OmniPhysCap (OPC) benchmark to evaluate the recovery of physical and cross-modal evidence from generated captions. Finally, we train OmniFysics-Captioner from the resulting data. Our Captioner matches Gemini 3.1 Pro on audiovisual captioning, achieves state-of-the-art results on multiple video-captioning benchmarks, and substantially outperforms other open-source models. Ablations show that PPM evidence improves physical coverage and produces finer-grained, more reliable cross-modal descriptions.

As large language models (LLMs) become capable of processing increasingly diverse modalities and longer temporal contexts, an emerging line of work is moving beyond fixed video-language inference toward agentic systems that actively decide what information to inspect, retain, verify, and act upon. This survey reviews video understanding agents: systems that use video as the primary information source and solve understanding tasks through adaptive state construction and action selection. We first formalize an agent loop for video understanding, then address a central question: why do agents matter for video understanding? To answer this, we organize the literature through a challenge-to-design taxonomy, linking context bottlenecks to hierarchical evidence memory, evidence sparsity to active evidence acquisition, temporal causality to state and process tracking, and multimodal ambiguity to role-specialized coordination. We further review state space paradigms, learning paradigms, supervision signals, benchmarks, and evaluation protocols. Finally, we identify open directions toward agentic-native temporal modeling and video-native agents. Project page: https://github.com/DXY0711/Awesome-Agentic-Video-Understanding

Multiple instance learning (MIL) is widely used in computational pathology because it enables weakly supervised analysis of whole-slide images (WSIs) without requiring patch-level annotations. In attention-based MIL, instances with high attention scores are often interpreted as diagnostically important regions and used as visual explanations. However, attention scores alone cannot determine whether selected high-attention instances are significantly different from normal instances, limiting the reliability of attention-based explanations. In this paper, we formulate the evaluation of high-attention instances as a statistical hypothesis testing problem. Specifically, we assess whether a selected high-attention instance significantly deviates from a representative normal reference instance selected based on feature similarity. A major challenge is that both the target instance and the reference instance are selected through data-dependent procedures, rendering standard hypothesis testing invalid. To address this issue, we introduce a selective inference (SI) framework that explicitly accounts for the selection events induced by attention-based instance selection and adaptive reference selection, thereby enabling the computation of valid selective $p$-values conditional on these events. Experiments demonstrate Type-I error control on synthetic and MNIST-based data and practical applicability to pathological WSIs, with higher statistical power than the conventional over-conditioning approach.

In 1984, Frank Harary introduced the first convexity games in graphs, all of them based on the geodesic convexity, which is the graph convexity related to shortest paths. In 2024, Araújo et al. obtained the first PSPACE-hardness proofs on some of these geodesic games and generalized them to any graph convexity. In this paper, we investigate convexity games on several known induced path convexities: the monophonic $\mathrm{m}$-convexity and the $\ell_k$-convexities, based on induced paths and on induced paths of size at most $k$. We prove that the hull games $\mathrm{CHG}_{\mathrm{m}}$, $\mathrm{CHG}_{\ell_k}$ and their misère variants are PSPACE-complete for every $k\ge2$ even in graphs with diameter at most 3. We also use the Sprague-Grundy Theory to obtain a polynomial time algorithm to decide the winner of the games $\mathrm{CHG}_{\mathrm{m}}$ and $\mathrm{CHG}_{\ell_k}$ for any $k\ge2$ in disjoint unions of paths and cycles. For $k\ge3$ odd, we prove that Alice (1st player) wins $\mathrm{CHG}_{\ell_k}$ in the path $P_n$ if and only if $n$ is odd and she wins in the cycle $C_n$ if and only if $n=3$ or $n=\alpha\cdot (k+1)-1$ with $\alpha\ge2$. For $k\ge2$ even, the only periodic nimber sequences of $\mathrm{CHG}_{\ell_k}$ obtained through extensive computational testing occurred for $k=2^h-4$ with $h\ge3$, e.g, $k\in\{4,12,28,60,\ldots\}$. In this case ($k=2^h-4$ with $h\ge3$), we prove that the nimber sequences of $\mathrm{CHG}_{\ell_k}$ in $P_n$ and in $C_n$ are periodic and Alice loses (resp. wins) in $P_n$ (resp. $C_n$) with $n>k$ only when $n=3k+4$ (resp. $n\in\{2k+1,5k+3\}$). Finally, we show that, for $k=2$, the game $\mathrm{CHG}_{\ell_2}$ in paths $P_n$ is closely related to the classical game Couples-are-Forever of J. H. Conway: it is still an open problem if the nimber sequence is periodic or not and Alice loses only for 12 values of $n$ up to $150$ million.

Oblique retrieval, as exemplified by OBLIQ-Bench, asks a retriever to find documents whose relevance is determined by a latent attribute (an implicit stance, an analogous reasoning technique, an authorial fingerprint, or a vague tip-of-the-tongue recollection) that has little or no surface expression in the document. State-of-the-art dense encoders and agentic search pipelines built around frontier language models exhibit a large first-stage bottleneck on these tasks, while the same language models reliably verify relevance when shown candidates. We address this with OBLIQ-IR, a single-vector dense retriever whose training mixture combines per-mechanism synthetic queries with a new form of cross-model supervision: kNN-graph distillation from a frozen authorship encoder, which transfers a style-versus-topic inductive bias into the student. A 3B retriever fine-tuned reaches 0.211 NDCG@10 on Writing-Style, 0.171 on Math, 0.177 on Twitter, and 0.281 on Congress, improving over the GPT-5.2 Multi-Hop Agent by \xr{0.010 to 0.150} NDCG@10 and over Gemini-2-Embedding by 0.027 to 0.222 NDCG@10 on every reported task. The code, data and checkpoints are available https://github.com/DataScienceUIBK/obliq-ir

Automatic failure recovery is another difficult area of DevOps deployments due to the complexity of the system, high workload and the limitations of the traditional rules-based or manual approach. This study proposes a hybrid model integrating deterministic, rule-based recovery with the assistance of machine learning by fault prediction to automatically monitor failures, identify, classify and recover failures in real time. To test the architecture, a distributed log dataset of 100,000 records was used for models such as Decision Tree, Random Forest, Logistic Regression, LightGBM, Autoencoder with BiLSTM. The Decision Tree had a strong performance in defect identification with an F1 score of 80.8%, recall of 80.0%, precision of 81.6%, and accuracy of 89.4%. An impressive 83.3% success rate was achieved by the automated recovery measures, resulting in a 94.6% decrease in mean time to recovery (MTTR), a 95.4% reduction in downtime, and annual savings of 7,462. The combination of explainable rule-based logic and adaptive AI prediction in the framework means it is more resilient, operationally efficient, and scalable, and an effective, autonomous approach to DevOps environments evaluated under controlled experimental conditions.

Agentic AI systems are increasingly adopting automated pipelines that integrate multiple tools. While prior research have studied task success and task completion of such agentic systems, research on agent to tool interaction chain via a wrapper and API, specifically in biological agentic workflows, remains limited. This study investigates specific failures in agent to tool interaction where a tool invocation appears successful but some or all of the information or functionality from the tool via its API / wrapper is incomplete or missing and there are no communications to the user or the agent regarding the missing information. We call these 'silent failures' because the user or the agents are not aware that such a failure has occurred. For the purpose of this study, we developed an audit mechanism to identify such silent failures in agent to tool interaction chains, by examining 15 scientific tools (and their associated API documentation and tool documentations) integrated within the ToolUniverse environment (ToolUniverse serves as our experimental environment rather than the object of the study itself). We structure our study around 7 failure locus, characterising where the failure occurs in the chain. We observed 91 failures (manually validated post LLM based candidate discovery and automated testing), most frequent of them being missing data or fields and inconsistencies in search, filtering or ranking criteria. Most of the 91 failures occurred in API layer (52) or wrapper layer (25), with a potential of silent failure amplification downstream. The results show that silent failures originate upstream of the event and propagate downstream into apparently valid scientific outputs. We propose a concept of contextual reliability to handle such failures and suggest mechanisms for testing, disclosing, monitoring, and measuring such failures across the agent-tool interaction pipeline.

COBOL remains widely deployed, yet representative corpora reflecting real production code are rarely available, limiting rigorous benchmarking of modernization approaches. We propose a systematic agentic AI pipeline for generating realistic COBOL programs, combining specification-driven generation with iterative degradation guided by patterns and complexity targets extracted from real production code. Here, realism is understood as structural fidelity to production code as captured by our metrics. We evaluate whether degradation reaches target complexity levels while preserving business behavior, and examine the limits of the approach, across three programs from distinct business domains. Results show the pipeline reliably produces syntactically valid programs and moves them toward realistic structural complexity. However, preserving business behavior is not always achieved by construction, and targeting structural metrics independently of business logic risks producing programs whose complexity does not reflect a plausible maintenance history. We discuss these limitations and outline a more realistic alternative as a direction for future work, generating legacy programs from scratch along a simulated development history.

Simulation success is not equivalent to structural correctness for LLM-generated circuits. We define and measure four evaluation levels – schema validity, topological validity, backend executability, and component-set agreement – on a 150-circuit trilingual benchmark, through a deployed pipeline built on a typed circuit interchange representation. The levels are not nested. On gpt-4o-mini, 16 of 150 circuits (10.7%, 95% CI 6.7-16.6) were rejected by the topological validator but executed in ngspice with no error or warning; 12 of these contained exactly the requested components, with one terminal disconnected. Conversely, 7 circuits (4.7%) passed the validator and ngspice refused them. Ten failed both checks and 117 passed both, so each check detects a class the other misses. A minimal three-component divider shows the cost: a dangling resistor reports 5.00 V instead of 2.50 V while ngspice stays silent. A paired ablation, in which every arm is evaluated from the same model sample rather than a fresh one, separates each repair stage from sampling noise. On a stratified 45-circuit subsample, model repair raised topological validity from 40.0% to 84.4% (+20 circuits, no regressions) while moving executability by a net 6 (+7, -1), an effect this sample size does not resolve, and component agreement by 2. One circuit moved in opposite directions at two levels in a single repair step. Against a direct-netlist baseline the pipeline executed 88.7% against 47.3%, or 62.7% under an accounting that credits the baseline with every failure we cannot confidently attribute to the netlist. These results support a narrow methodological conclusion: structural validation and simulation should be reported as distinct evaluation stages for LLM-generated circuits. A circuit that runs is not necessarily structurally valid, and a structurally valid circuit is not necessarily executable.

Rapidly growing AI workloads are driving large investments in AI datacenters. This survey classifies industrial AI accelerators into four architectural categories and compares their compute and memory organizations. It examines how node-, rack-, and pod-scale interconnects support collective communication, and traces architectural evolution across accelerator generations. The analysis connects advances in arithmetic throughput with changes in precision, data delivery, execution coordination, communication, power delivery, and cooling. It also discusses future design challenges arising from workload diversity, data movement, infrastructure constraints, and model evolution, showing how the trade-off between generality and specialization extends from individual accelerators to datacenter-scale systems. GitHub: github.com/Yufeng98/AI-datacenter

With sparse and event-driven computation, spiking neural networks show great potential for achieving accurate and power-efficient UAV visual tracking. However, existing SNN-based trackers typically use spike firing rates only for power consumption and lack explicit optimization of actual spike activity. Moreover, regulating spike activity alone does not explicitly encourage stable target representations under partial observations and temporal appearance changes. We propose SBMVTrack, a fully spiking tracking framework that combines spike activity regulation with complementary multi-view representation learning. Specifically, SBMVTrack introduces Energy-Weighted Spike Budgeting (EWSB), which incorporates layer-wise computational costs when regulating spike firing rates and penalizing saturated activations, thereby reducing redundant spike computation. To further improve target representations under the spike budget constraint, we introduce Masked Multi-View Target Modeling (MVTM), which treats the initial template, online template, and search region as temporal views of the same target. By aligning target embeddings between masked and corresponding unmasked views and enforcing cross-view identity consistency, MVTM encourages robustness to missing local cues and temporal appearance changes. Experiments on four UAV benchmarks demonstrate competitive tracking performance with a 24.1% reduction in estimated power consumption relative to the baseline. On VisDrone2018, SBMVTrack achieves a success rate of 70.0%, exceeding SpikeTrack by 9.7 percentage points while reducing estimated power consumption by 45.7%. The source code will be released upon acceptance.

Assigning a standard commodity code to a free-text purchase line underpins enterprise spend analytics, and its reported accuracy cannot be checked. Published results use proprietary data or private samples under undocumented protocols; no two compare and there is no public benchmark. We build a harness with four protocols over 1.26 million labelled purchase lines from two US state governments. Enterprises rebuy continuously, so random splits put matching item text on both sides: 60.7% and 61.2% of test rows, 54.7% and 60.6% byte for byte. On California orders the best classical baseline scores 56.0% on repeated text but 31.9% on novel text, a 24-point gap widening with taxonomy depth. Embedding retrieval shrinks the gap from 23.8 to 19.1 points; a fine-tuned transformer does not escape it. On one corpus leaky evaluation cannot separate retrieval from the transformer, while three leak-free protocols put the transformer 2.3 to 3.6 points ahead, so leaky splits hide real differences, not just flatter both. We derive an upper bound on text-only classifiers from identical text with conflicting codes: 79.4% commodity accuracy on one corpus against 98.4% on the other, so accuracy does not compare across datasets. Spend-weighting the bound reflects the amount field more than labels. In a deployment of 920,927 lines, reviewers accepted 32.4% of suggestions on the novel-text population; 29.7-35.2% brackets benchmark rates near 31.9% and 34.8%. We release the harness in production use.

We present the first method for native, continuous gradient descent for machine learning models with $p$-adic parameters. Existing native optimizers are discrete, mostly combinatorial searches, as the $p$-adic numbers $\mathbb{Q}_p$ are totally disconnected, with standard losses that are flat away from their minima. To enable continuous optimization, we propose working with $\mathbb{Q}_p$ via its Berkovich affine line: a canonical, path-connected expansion of $\mathbb{Q}_p$ that preserves its isometries and uniquely extends its analytic maps. This hull is a metric tree with interpretable points and local derivatives, which we show enables effective optimizers and backpropagation. We formulate gradient descent and show that its approximations efficiently learn linear models with coefficients in $\mathbb{Q}_p$ to do modular arithmetic, an XOR-like task not expressible by linear models in $\mathbb{R}$. We also demonstrate momentum and Adam variants, linear regression, and classification on binary-encoded hierarchies (Quillian semantic networks), addressing open problems posed by Martins (2025). Library at https://github.com/google-deepmind/padic-ml

Training data quantity and quality greatly affect object detection model performance, regardless of model architecture. For object detection in deep-sea video and imagery, where the objects of interest (primarily organisms) are sparse, faint, and hard to identify, incremental improvements to detector performance may require an iterative approach to data labeling and management. This paper presents mbariml, a Python-based video and image analysis pipeline built around the data labeling and management process. mbariml uses an Ultralytics YOLO detection model, runs it over still images or video, stores every detection as a reviewable region of interest, groups those regions by visual similarity so that a human can accept or reject them in bulk, and exports the result as training data, statistics, image sidecars, and additional metadata. Existing YOLO and Pascal VOC datasets can be imported into the same database, so a legacy training set can be reviewed, extended, and re-exported alongside new detections. The human review stage is the center of the design: an annotator can validate, relabel, resize, delete, and draw entirely new localizations, optionally assisted by the SAM3 segmentation model, and every one of those edits is written back to the same database the detector wrote to. Video receives particular attention: the software treats each tracker-produced track as a provisional observation and selects one representative frame instead of retaining every detection in the track. We describe the pipeline stage by stage, including how each track's representative frame is chosen (from a user-selected third of the track, the middle by default), which we examine on 684 tracks from seafloor video.

Deploying Large Language Models for runtime operational triage incurs prohibitive latency (>100-500 ms), high VRAM requirements (>4-8 GB), and excessive energy dissipation. Extending Mandelbrot Fractal Neural Synthesis (Dagli et al., 2026), this paper presents the Universal Fractal Natural Language Decision Map, realized via the werr machine-native edge reflex runtime and the production answerr platform (https://answerr.me). Operating entirely without stored weight tensors (0 Bytes VRAM), the engine synthesizes deterministic decisions—noul (Boolean), choice (categorical), and score (ordinal)—by dynamically modulating 24-byte coordinate seeds along the chaotic boundary of the Mandelbrot set and evaluating multi-scale escape dynamics. Drawing inspiration from biological System-One reflex arcs, the engine introduces: (i) an Auto-Seed Router with domain projector Phi_D yielding a +28.8% accuracy gain over linear baselines; (ii) an Information-Theoretic Semantic Token Damping Filter (T_desc = 0.045) insulating against prompt injections (0.0% empirical bypass; 95% Wilson CI: [0.0%, 27.8%]) while pruning iterations by 45.8% (accelerating throughput 2.5x to 3.31 ms latency); (iii) a Multi-Scale Harmonic Tripod Fusion; (iv) a Coupled Margin Expansion Operator (Pitchfork Bifurcation Offset); and (v) a Cyclic Z/9Z Modular Resonant Grid Discretization based on the closed sub-ideal {0,3,6} (Lean 4 Mathlib ZMod 9), reducing FLOPs by 68.4%. Evaluated on JevBench (N=231), werr achieves 100.00% TypeSafe compliance and 81.65% calibrated accuracy with 7.08 ms median latency. We provide an OpenAI-compatible API and demonstrate deployment on 32-byte EVM smart contracts via the open-source werracle on-chain oracle (21,438 gas).

In this paper, we motivate the need for a participatory speech dataset creation framework through a case study of the LGBTQIA+, or queer, community - a community with documented concerns about AI and reported harms, including attempts to develop 'gaydar' technologies that purportedly identify individuals as queer. We review common speech data collection practices, why these methods may be unsuitable for engaging with queer speakers, and discuss previous efforts in participatory AI with queer community engagement, as well as participatory endeavours specific to speech data collection for other marginalized communities. From this review, we develop a conceptual framework for participatory speech data curation by, for, and with marginalized communities drawing on insights from co-design and knowledge sharing. We propose a framework comprising overlapping and two-way processes of defining a community, project formulation, modes of participation, and personal autonomy.

Large vision-language models (VLMs) can be efficiently deployed under stringent memory and latency constraints through post training quantization (PTQ). However, most PTQ methods are designed for unimodal large language models (LLMs). These methods treat quantization errors as isotropic perturbations under the Euclidean assumption, which provides weak guidance on directions most sensitive to quantization in VLMs. Consequently, directly adapting unimodal PTQ approaches or solely employing modality-specific scaling often leads to uneven bit-width distribution and inconsistent performance in low-bit settings. To address these challenges, we propose Riemannian Geometry-Sensitive Quantization (RGSQ), which formulates quantization as a reconstruction problem under a unified Fisher-Riemannian metric. RGSQ identifies modality-specific sensitive directions via Riemannian manifold mappings built from modality-partitioned empirical Fisher factors and fused into a modality-aware Kronecker-structured metric. We then apply geometry-aligned rotations to reorient the local tangent frame, steering low-bit perturbations toward loss-insensitive axes. Finally, we apply a whitening transformation that maps the Riemannian objective to an equivalent Euclidean form, enabling standard unimodal PTQ methods to evaluate multimodal quantization error under their original assumptions. Across an extensive and diverse set of mainstream VLM benchmarks, RGSQ achieves the highest accuracy and stability under extremely low-bit settings (W2A8 and W3A8). It outperforms VLM-aware baselines, such as MBQ and MQuant, by up to 5.9% and surpasses single-modality improvements by up to 8.6%.

In this paper, we examine speech datasets for their inclusion of LGBTQIA+, or queer, voices and provide a taxonomy of tensions to better understand why there is a lack of such voices in current speech technology datasets. Through an audit of six diverse speech datasets, we find that measurable queer representation is low (0-1.4% of speakers) - insufficient for robust disparity measurement. We take this community as a case study to consider what challenges and tensions are associated with collecting speech data from marginalized communities. For comparison, we audit an additional two datasets from the speech sciences that were created by, for, and with the queer community. We note that many customs in speech dataset collection efforts in AI and speech technology research may conflict with values emphasized in participatory approaches with marginalized communities, and provide a taxonomy describing these tensions.

Consistent multi-view object segmentation is critical for 3D perception and robotics, yet remains challenging under severe viewpoint and occlusion changes. Existing methods typically perform 3D instance segmentation on point clouds or rely on offline 2D mask-matching pipelines. However, 3D instance segmentation is limited by scarce 3D annotations, while offline 2D matching suffers from object identity ambiguity across frames. To leverage strong 2D and 3D priors jointly, we propose SAM-V (Geometry-Aware Segment Anything for Multi-View Instance Segmentation). Instead of combining the two priors through post-hoc matching, SAM-V directly integrates features from a feed-forward geometry model (VGGT) into a 2D segmentation foundation model (SAM), trained end-to-end for cross-view instance prediction. SAM-V introduces a prompt-fusion mechanism that enriches sparse SAM prompt tokens with view-specific camera tokens and local VGGT features, making the prompt representation both view-aware and spatially grounded, together with a mask decoder that attends to dense 2D and 3D features. By conditioning the mask decoding directly on multi-view geometry, SAM-V produces consistent multi-view segmentation of a prompted object in a single forward pass without offline mask matching or explicit 3D reconstruction. On the IGGT 3D tracking benchmark, where consistent instance identity across frames directly determines performance, SAM-V improves overall IoU by 5 points and frame-level recall by 12 points on the ScanNet++ split over the state-of-the-art multi-view instance segmentation baseline and leads on all metrics in the zero-shot ScanNet split. Our code and pretrained models are available at https://github.com/gong208/SAM-V.git.

In this paper, we develop a high-order variable-scaled energetic variational neural network (VS-EVNN) method for phase-field gradient flows. Each discretization stage uses an updated-state network whose spatial inputs are centered and divided by the interface scale, while the sampled energy and movement penalties remain unchanged relative to the baseline EVNN formulation. This rescaling is motivated by a coordinate change in the energy that normalizes the gradient coefficient of the transformed functional. We combine the scaled representation with high-order, multi-stage variational extrapolation schemes and a heuristic adaptive time-stepping controller. Each stage is solved as a network minimization problem, in which the earlier stages serve as fixed anchors on the quadrature grid, yielding a neural realization of these multi-stage variational schemes, including a mobility-weighted, mass-conserving version for Cahn–Hilliard flows. The method is tested on one- and two-dimensional Allen–Cahn and Cahn–Hilliard flows, the latter in the mass-conserving metric. Under the reported optimization settings, the scaled networks yield lower solution errors than the unscaled EVNN baseline, and the higher-order schemes improve the accuracy in the test examples.

Models that predict which Google Play apps will be removed are trained on labels that record only whether an app was still in the store at a later observation. A disappeared app is labeled removed and a present one stable, but neither records why. A voluntary withdrawal and a policy takedown both produce removed, and an uncaught spam app keeps stable. This work calls that mismatch label noise. Three detectors from different methodological families are applied to the 870,514 apps of Mohsen, Karastoyanova, and Azzopardi (2022): Isolation Forest, flagging apps unusual in the feature space, Neighborhood Disagreement, flagging apps whose nearest neighbors carry the opposite label, and Prediction Inconsistency, flagging apps a classifier labels differently from the data. The apps flagged by all three, the overlap, number 7,598 at default settings and are the strongest mislabeling candidates. Two questions follow. First, does removing flagged apps improve the model? It does not. No detector, overlap, or union beats the baseline, and the loss grows with the number removed. Second, do flagged apps appear less often than expected among apps whose label VirusTotal and Quark Engine confirm? Among confirmed removals they do, falling to 0.43 times the expected rate as the threshold tightens, while an excess on the stable side disappears once the age of the scanned apps is accounted for. A model trained on only the 3,021 trainable overlap apps reaches a test AUC of 0.2518, far below chance, so the relationship between features and labels there runs opposite to the rest of the data. The flagged apps run wrong in both directions: abandoned apps that resemble spam carry stable, while apps that look healthy carry removed. The value of the detectors lies in characterizing this label noise. They locate a small set of candidates they cannot profitably remove.

Forceful manipulation is challenging for humanoid robots because interaction forces can disturb whole-body balance. We introduce the Supporting Hand Strategy (SHS), which enables a humanoid to brace against the environment with one hand while performing forceful manipulation with the other. SHS optimises a task-conditioned support configuration that guides two synchronous reinforcement-learning policies, without human motion data or online whole-body trajectory planning. On a Unitree G1, SHS achieved usable contact forces up to 60 N, compared with a maximum sustained force of 13.5 N without environmental bracing, while substantially improving force tracking over a task-independent support configuration. The same policies generalised to different task regions without retraining. SHS therefore provides a simple mechanism for substantially extending humanoid forceful-manipulation capability.

Smart meter (SM) data provides fine-grained visibility into household energy consumption, but also exposes users to privacy risks. Inference attacks, known as non-intrusive load monitoring (NILM), can perform appliance-level inference from aggregate signals and recover sensitive behavioral patterns. In practice, attacker models are unknown and heterogeneous, making robust defense challenging. We formulate SM privacy protection as a black-box inference defense problem, aiming to reduce the recoverability of appliance-level information while generalizing across diverse and unseen attackers. We propose a proxy-guided hierarchical reinforcement learning framework that learns battery-based load-shaping policies to inject realistic but misleading appliance-level signatures into the aggregate signal, thereby disrupting the structured patterns exploited by NILM. A self-supervised aggregate-structure privacy probe provides a reconstruction-error-based surrogate reward for disrupting recoverable load structure, while a signature library makes the perturbations appliance-relevant and physically realizable through battery control. We provide theoretical rationale showing that proxy-guided optimization improves inference robustness under attacker diversity. Experiments on real-world datasets UK-DALE and REDD demonstrate strong cross-model and cross-appliance generalization. Across six unseen NILM attackers, covering four appliances on UK-DALE and five on REDD, our proposed defense increases average appliance-level RMSE by 107% and 166%, respectively, while reducing F1 score by 79% and 80%.