Computer Vision · Cross-listed from eess.IV
RePrior: Measurement-Reconciled Prior Correction for Sparse-View CBCT Reconstruction
Mengrui Yin, Tianxingjian Ding, Wufan Zhao et al. (+2 more)
Sparse-view cone-beam computed
tomography (CBCT) is severely under-constrained by limited X-ray projections. Learned reconstruction can provide complementary anatomical information, but using it as a prior in patient-specific Gaussian reconstruction introduces two challenges. First, the discrepancy between the learned prior and current reconstruction is spatially non-uniform: some local differences contain useful missing 3D information, whereas others reflect prior bias. Second, even a volumetrically beneficial correction can conflict with the observed X-ray measurements. Since X-ray measurements are line integrals, spatially separated corrections may affect overlapping rays, with their signed projection responses reinforcing or partially canceling in the measurement residual, so their feasibility cannot always be assessed independently. In this paper, we introduce RePrior, a multi-stage progressive prior-correction framework that addresses correction actionability, measurement feasibility, and representation expressivity. Selective Correction Proposal (SCP) first identifies actionable signed local corrections from prior–reconstruction discrepancies. Measurement-Constrained Reconciliation (MCR) then jointly enforces their consistency with patient-specific X-ray measurements, while Hybrid Residual Enhancement (HRE) recovers additional correction capacity through complementary voxel- and Gaussian-domain degrees of freedom around the reconciled anchor. RePrior requires neither test-time ground truth nor case-specific network fine-tuning. RePrior gains approximately 2.6~dB in 3D PSNR over R$^2$-Gaussian across LUNA16, PANORAMA, and PENGWIN. Beyond prior-assisted reconstruction, it delivers additional gains in volumetric quality and observed-view projection fidelity, with consistent gains in held-out-view fidelity in the backbone-matched evaluation.
Read the full abstract ▾
All authors Mengrui Yin, Tianxingjian Ding, Wufan Zhao, Ziyang Yan, Yu Tian
Computation and Language
Fin_Agent at FinEval 2026: Task-Aware Methods for Multilingual Financial NLP
Mohotarema Rashid, Tanzina Hossain, Xiaoying Song et al. (+1 more)
We present Fin_
Agent, our submission to the FinEval 2026 shared task on multilingual fi nancial
language understanding. Our sys tems address Greek financial named-entity recognition, Japanese implicit communication recognition, and multilingual financial ques tion answering. For Greek NER, we com bine annotation-aware numeric rules with zero shot Qwen2.5-32B classification, achieving 0.9521 public F1 and 0.8884 private F1. For Japanese implicit communication, an inter pretable cue-based ordinal scorer achieves 98.0% test accuracy. For multilingual financial QA, BGE-M3
retrieval with Qwen3-32B gen eration achieves 0.3023 and 0.3419 ROUGE-1 F1 on the public and private splits. Key limita tions include
dataset-specific rules, handcrafted cues, and limited supervision. Implementa tion code is available https://github.com/ Rashidnira/finagent-fineval-2026.
Read the full abstract ▾
All authors Mohotarema Rashid, Tanzina Hossain, Xiaoying Song, Lingzi Hong
Computational Geometry · Cross-listed from math.CO
Symmetric, rational and infinitely many $(23_4)$ configurations, and the end of the existence problem for geometric $(n_4)$ configurations
Wenhao Lu
A
geometric $(n_4)$ configuration is a set of $n$ points and $n$ lines in the real projective plane such that every point lies on exactly four of the lines and every line contains exactly four of the points. The question of which $n$ admit such a configuration was posed by Grünbaum in 2000, and successive work of Bokowski, Grünbaum, Schewe, Pilaud and Cuntz settled every case but $n=23$. We settle this last case by bounding the
symmetry of such configurations and classifying the most symmetric ones exactly. We prove that for every
prime $n\equiv3\pmod4$ the group of projective
symmetries of a
geometric $(n_4)$ configuration has order at most four, explaining why symmetric constructions failed at $n=23$, and the same argument bounds the
symmetry of $(n_5)$ configurations for
primes $n\not\equiv1\pmod5$. Reducing the Klein four-group case to 4021 bilinear
polynomial systems and solving all of them exactly with Gröbner bases, we show that exactly two $(23_4)$ configurations reach this bound up to projective equivalence and that there are no others even over $\mathbb{C}$. Both are self-polar; the first has integer coordinates and the second is defined over $\mathbb{Q}(\sqrt{17})$ but not over $\mathbb{Q}$. Consequently
geometric $(n_4)$ configurations exist if and only if $n\ge18$ and $n\ne19$. The same classification recovers Cuntz's $(22_4)$ and $(26_4)$ configurations and finds three new combinatorial types at $n=22$ and $94$ at $n=26$. Among self-polar $(23_4)$ configurations with a single involution we find $50$ more, defined over number fields of degree at most $7$. Four of them deform in one-parameter families, and computing three of these exactly, one birational to the modular curve $X_1(11)$, we prove that there are infinitely many
geometric $(23_4)$ configurations, among them infinitely many with rational coordinates that are self-polar and have no projective
symmetry.
Read the full abstract ▾
Machine Learning
From Prototype to Massing: Learning Graph Correspondence for Scalable Facade Modeling
Yiliang Shao
Facade articulation at building scale is usually resolved manually or through parametric systems that encode design intent as explicit rules. This paper investigates a complementary workflow in which a designer-authored prototype supplies transferable articulation logic. Prototype and target massing are represented as heterogeneous attributed graphs, and a Siamese graph
attention network with instance-local triplet supervision embeds their segments in a shared metric space. Many-to-one nearest-neighbor
retrieval then routes prototype Patterns to the larger target. On the original 85/15 within-corpus holdout, prototype-to-massing top-1 accuracy reached 96.5%, compared with a reported 76.5% raw-feature baseline. A Rhino demonstrator converts predicted correspondence into reusable facade Patterns, and qualitative applications on four built projects show the workflow across distinct massing organizations. The contribution is not automated facade generation, but an authoring model in which resolved geometry serves as a computational specification for project-scale propagation.
Read the full abstract ▾
Machine Learning
A Physics-Informed Hybrid Forward-Inverse Machine Learning Framework for High-Dimensional Sparse Recipe Reconstruction
Md. Muqtadir Fuad, Md. Istiak Adnan and Ridwan Al Aziz
High-dimensional sparse recipe formulation in process industries involves nonlinear association of various
covariates, bounded by sparsity constraints and multi-criteria tolerances. Traditional physics-based classical methods (such as Kubelka-Munk) fail to generate sparse candidate recipes properly due to their simplified assumptions and industrial process variations. This study proposes a hybrid physics-informed uncertainty-aware framework that is structured into three modules: (a) Module A, a multi-target forward quality model; (b) Module B, a sparse inverse reconstructor; and (c) Module C, a feasibility-constrained ranking layer. Then it has been validated in an industrial textile dyeing context with recipe-grouped cross-validation under multi-illuminant quality assessment comprising process and production information, target reflectance, K/S values, and spectral descriptors. Histogram Gradient Boosting (HGB) with spectral-only features ($R_\lambda$, K/S) and Gradient Boosting Regressor (GBDT) with recipe-process features outperforms other configurations with out-of-Fold MAE of 0.1655 and 0.1523 in the forward quality model. For inverse reconstruction, a component-wise median blend achieved a recipe-vector MAE of 0.0295. Exploratory conditional treatment effect (CATE) suggests an observational association that alkali adjustment reduces error for red and pale shades (CATE = -0.196). This framework provides a human-in-the-loop decision-support tool that minimizes costly laboratory trials across industrial formulation domains.
Read the full abstract ▾
Software Engineering
SWEeper-Bench: Can Agents Discover Bugs in Interactive Software?
Yang Yao, Haozhe Chen, Bingyi Kang et al. (+2 more)
Coding
agents increasingly interact with users by generating interactive software on the fly rather than replying in text, yet many bugs in such software reveal themselves only after multi-step interactions. Today, users must discover these bugs and wait for fixes, making the development loop slow and expensive. Existing
benchmarks typically assume the bugs have already been identified, leaving
agents' ability to find interaction-dependent failures largely unevaluated. We introduce SWEeper-Bench, 200 tasks built from real bug fixes in 200 widely used open-source web applications. Each task gives the
agent only the codebase and an open-ended request such as "Find and fix issues in Focalboard's board sharing and membership." Because these bugs are hard to detect from code alone,
agents must design interactive tests to uncover them. An agentic verifier then judges each repair by what a user would observe in the browser. The best of 15 frontier
agents passes only 59.0% of tasks. Through stage-by-stage analysis of
agent trajectories, we show that the biggest bottleneck is identifying the buggy behavior:
agents often reach the relevant feature but never trigger the failure or fail to recognize it. SWEeper-Bench measures progress toward
agents that close this loop themselves, delivering software that works without waiting for user feedback.
Read the full abstract ▾
All authors Yang Yao, Haozhe Chen, Bingyi Kang, Karthik R Narasimhan, Zhuang Liu
Systems and Control · Cross-listed from q-bio.NC
Energy, Information, and the Limits of Neuropsychiatric Classification
Farbod Khodadadi, Mina Kheirkhah, Bita Shariatpanahi et al. (+15 more)
Importance: The search for reliable neuroimaging biomarkers of mental disorders has remained elusive despite decades of research. Why clinically consequential disorders yield weak neuroimaging separability remains unresolved. Drawing on statistical thermodynamics and the metabolic costs of neural coding, we propose that psychiatric disorders produce constrained deformations of a largely shared repertoire of
brain activity patterns, limiting the class-specific information available for classification. Observations: We develop a framework linking physical resource constraints, landscape deformation, distributional separation, and attainable classification, and examine its components using human neuroimaging, synthetic data, and an exactly specified physical model. In resting-state fMRI from 1952 FOR2107 participants (823 with major depressive disorder; 1129 healthy controls), held-out energy-landscape estimates and nonlinear classifiers agreed across 13 comparisons (r = 0.996). Similar results emerged at both FOR2107 centers and in 900 SRPBS participants spanning multiple psychiatric diagnoses. In synthetic data, classification improved with distributional separation and approached the optimum. In an
equilibrium three-well model, statistical energy equaled physical potential energy scaled by inverse temperature. Modest deformation redistributed state occupancy while optimal snapshot classification remained weak. A literature map found insufficiently comparable evidence to test the human metabolic constraint. Conclusions: Clinically consequential differences may arise within a largely shared neural repertoire. The thermodynamic framework connects physical deformation to classification under specified assumptions; its metabolic implementation in humans remains untested. Testing this mechanism requires joint measurements of
brain activity, bodily physiology, and metabolism.
Read the full abstract ▾
All authors Farbod Khodadadi, Mina Kheirkhah, Bita Shariatpanahi, Sarah Alizadeh, Madleen Stenger, Amaia Zurinaga Gutierrez, Shakiba Bakhshian, José C. García Alanis, Nils R. Winter, FOR2107 Consortium, Frank Bremmer, Stefan G. Hofmann, Udo Dannlowski, Tilo Kircher, Sharmili Edwin Thanarajah, Igor Nenadić, Tim Hahn, Hamidreza Jamalabadi
Computer Vision
Scenes as an Attack Surface: Uncovering Scene-Grounded Safety Failures in MLLMs
Tongxi Wu, Yuyang Cheng, Jiacheng Xian et al. (+5 more)
Existing jailbreak attacks have exposed serious safety weaknesses in
multimodal large
language models (MLLMs). Most prior attacks rely on specially constructed visual inputs to carry or support harmful intent. In this paper, we uncover a different vulnerability: task-relevant scene semantics alone can shift an MLLM from refusal to compliance, even when the visual input introduces no additional attack instructions and the original task intent remains unchanged. We formalize this failure as a scene-grounded visual safety vulnerability and introduce SceneSafetyBench to investigate it across eight risk categories and nine white- and black-box MLLMs. Our analysis reveals that this failure is associated with how task-relevant visual evidence influences downstream safety representations, suggesting that visual grounding alone cannot fully explain the observed safety shift. Building on this finding, we propose Scene-Grounded Attacks (SGA), which preserve the original task while constructing validated scene-grounded queries and combining their independent responses. Across nine target MLLMs, SGA achieves an average attack success rate (ASR) of 86.17%, outperforming the strongest baseline by 8.55 percentage points and achieving the highest ASR on eight models. Our results identify scene semantics as an overlooked attack surface in MLLMs and highlight a growing tension between stronger visual grounding and robust
multimodal safety
alignment.
Read the full abstract ▾
All authors Tongxi Wu, Yuyang Cheng, Jiacheng Xian, Hu Huang, Zhihao Wu, Menglin Yang, Jian Zhang, Yang Gao
Computer Vision
Human Pose Estimation by Probabilistic Mixtures of Gaussian and Uniform Distributions
Santiago Reina Alguacil and Ezequiel López Rubio
Despite advancements in sub-pixel decoding, modern Human Pose Estimation (HPE) architectures remain constrained by deterministic coordinate extraction from discrete heatmaps, which systematically fails under dense occlusions and Out-of-Distribution (OoD) ambiguities. To address these limitations, we propose a post-hoc continuous probabilistic framework that intercepts raw heatmaps and models them as a Gaussian Mixture Model (GMM) augmented with a spatially agnostic uniform distribution, requiring no architectural modifications or retraining. This continuous representation allows us to comprehensively explore the distinct contributions of density modeling to HPE. We show that the spatial expectation of our fitted GMM achieves precision parity with leading sub-pixel decoders without heuristic post-processing. Leveraging this continuous space, our test-time augmentation aggregates probability distributions rather than discrete activations, mitigating multi-scale heatmap poisoning. Furthermore, because our
multimodal GMM parameterization isolates competing spatial hypotheses, it naturally interfaces with
geometric regularizers such as Markov Random Fields. However, our analysis exposes the inherent vulnerabilities of 2D kinematic priors under perspective foreshortening and visual degradation. Crucially, this density formulation yields significant improvements in uncertainty quantification: our calibrated
geometric covariance volume outperforms standard peak-intensity heuristics in OoD anomaly detection under severe occlusion. For in-distribution calibration, dynamically fusing our
geometric metric via Adaptive Softmax reduces or matches baseline Area Under the Sparsification Error (AUSE) across
benchmarks and degradation levels. Finally, we establish that this continuous parameterization is extensible to multi-view 3D architectures, bypassing the $\mathcal{O}(N^3)$ voxel
memory bottleneck.
Read the full abstract ▾
Programming Languages
Lava: Foundations for Liquid Haskell via Translation to Rocq
Colin Rothgang, Loïc Peyrot, Yannick Forster et al. (+2 more)
Liquid Haskell is an extension of the Glasgow Haskell compiler (GHC) that adds support for refinement types: types restricted by logical predicates. Specifications are automatically checked by an SMT solver, thus offering lightweight verification directly within the
language. However, the necessarily large trusted codebase behind
Liquid Haskell (from GHC to the SMT solver to the refinement typechecker itself) raises the question of trust in the verification and the necessity for a formalized semantics of
Liquid Haskell linked to its implementation. Grounding
Liquid Haskell in theory is complicated by the interaction between two semantic levels in the
language: a computational one and a logical one (for refinement predicates). While both are well understood separately, their interaction is subtle and has only been partially described. We give a semantics to
Liquid Haskell by translation to Rocq. Both the computational and logical parts are translated to the same
language, with a well-understood semantics; our translation makes the discrepancy between the two semantic levels explicit. The translation is implemented in Haskell and comes with a Rocq library that includes powerful proof automation standing in for the SMT solver. Thus, on the practical level, our tool Lava serves as a certificate checker for the supported subset of
Liquid Haskell.
Read the full abstract ▾
All authors Colin Rothgang, Loïc Peyrot, Yannick Forster, Michael Greenberg, Niki Vazou
Computer Vision
Pristine Models
Anirudh Sundara Rajan, Krishna Kumar Singh, Richard Zhang et al. (+1 more)
Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting the training data ensures safety, but reduces quality because examples containing unsafe concepts also provide useful knowledge that is not itself unsafe. Existing approaches largely address this trade-off post hoc through concept unlearning, which can lead to catastrophic forgetting as the number of concepts to remove grows. We instead ask whether unsafe concept knowledge can be compartmentalized during pretraining so that access to it can be disabled at inference. We introduce Pristine Models, a novel text-to-image generation architecture with an
attention mechanism that encourages the separation of safe and unsafe knowledge into independently parameterized branches. The branch-specific parameters are learned during training, while the unsafe branch can be detached at inference. On ImageNet, Pristine Models enable safer generation while retaining much of the utility of full-data pretraining, achieving higher image quality and better text
alignment than training only on safe data or applying post-hoc concept removal. We further scale our approach to CC12M, demonstrating that it remains effective in a substantially larger and more diverse open-world pretraining setting.
Read the full abstract ▾
All authors Anirudh Sundara Rajan, Krishna Kumar Singh, Richard Zhang, Yong Jae Lee
Robotics
When pose graphs are not enough: a failure analysis of pose-graph-based camera estimation for Gaussian splatting
Senthil Palanisamy, Azwad Sabik, Alan Dolhasz et al. (+1 more)
Exterior Gaussian-splat twins for real-estate listings are captured to a fixed recipe: a consumer drone orbits a single property in several overlapping passes at stepped altitudes, with occasional vertical ascents, so the imagery is dense, sequential, GPS- and time-tagged, and revisits each facade from many angles. This structure is tantalizing: it suggests camera poses could be recovered by a dense pose-graph optimization (PGO) whose only unknowns are the poses, far fewer than the joint pose-and-point problem bundle adjustment (BA) solves. PGO is mature in robotics, but almost always as post-processing: it redistributes the drift of an already-decent trajectory once loop closures tie it together. Splatting captures push that regime to its limit, every frame closing loops with dozens of others, raising a clean question: does pose-only optimization reach BA accuracy? We built a system specialized to this capture structure, not a general-purpose SfM tool, to test it. It beat COLMAP on speed but never on quality; this paper is the candid post-mortem. The shortfall arises from several interacting causes, hand-set weights, greedy merging and a noisy GPS ruler, together with two limits inherent to the formulation: SE(3) edges carry no scale degree of freedom, so independently scaled sub-maps drift when merged, and a two-view edge stops short of the coupling one 3D point imposes on every frame that sees it. A viable design must add back Sim(3) constraints, absolute GPS priors, retained structure, and uncertainty-aware weighting
Read the full abstract ▾
All authors Senthil Palanisamy, Azwad Sabik, Alan Dolhasz, Mira Slavcheva
Cryptography and Security
SAGE: Efficient Protected Vision-Language Inference on Smart Glasses
Zhimin Li, Pan Wang, Jingxian Chen et al. (+3 more)
Smart glasses are a promising platform for
vision-
language assistants, but private split inference remains expensive: protecting visual representations before transmission does not remove the cost of on-device
vision encoding, wide protected
tokens, or hardware-unaware execution. We present SAGE (Smart-glasses-Aware Guarded Encoding), a hardware-aware framework for efficient protected VLM inference on smart glasses. SAGE keeps raw images and unprotected visual
tokens on the trusted device, reduces visual input cost, executes shape-specialized INT8 graphs, and compresses protected representations into compact 256-dimensional INT8 packets before transmission. Unlike efficiency methods optimized only for nominal model size, SAGE selects its operating point using downstream answer quality together with measured latency,
memory, and thermal behavior on real Mentra Live glasses. On a matched Qwen workload, SAGE reduces glasses inference latency by 39.18%, device-sensor temperature rise by 21.91%, and protected packet size by 96.56%, while retaining 85.62% of the protected reference's relaxed utility and comparable prompted containment. Direct glasses-to-phone tests deliver all 192 packets and reduce median packet-plus-acknowledgment time from 71.3 to 10.0 ms. The compact protected interface also transfers across four additional VLM families. These results show that private wearable VLM inference must be optimized jointly across representation protection, communication, and real-device execution rather than through model compression alone.
Read the full abstract ▾
All authors Zhimin Li, Pan Wang, Jingxian Chen, Yuantao Tang, Qian Lou, Jingtong Hu
Discrete Mathematics · Cross-listed from math.PR
Satisfiability and freezing in random integer programs
Dylan J. Altschuler, Ruben Ascoli and Will Perkins
We study a model of a random centrally symmetric polytope and ask about the existence of points in the polytope with non-zero, integer coordinates. Our main results are the location of a sharp threshold for the existence of these integer points, a characterization of the typical empirical distribution of their coordinates, and showing that near the feasibility threshold these integer points are almost always totally isolated — at linear Hamming distance to the nearest other integer point in the polytope. The behavior of these random integer programs is related to that of the symmetric binary perceptron (the case when coordinates of points are $\pm 1$-valued). The lack of
symmetry in the set of potential solutions leads to new questions and phenomena, such as the distribution of the coordinate sizes in typical solutions, and requires the development of new information-theoretic techniques to deal with higher-dimensional optimization problems arising in the method of moments.
Read the full abstract ▾
Robotics
SenseWeather: Multimodal Sensing for Robust Robotic Perception under Extreme Conditions
Fucai Ke, Sukai Huang, Junyi Hao et al. (+4 more)
Robotic perception must remain reliable when extreme environmental conditions severely degrade the primary RGB observation. Although robotic platforms commonly carry complementary sensors such as depth and infrared, much of the modern perception stack remains RGB-centric, creating a mismatch between
multimodal onboard sensing and pretrained downstream models. We study whether complementary sensing can be used upstream to recover a task-compatible RGB observation that preserves existing perception capabilities without modifying or retraining the downstream stack. To this end, we introduce SenseWeather, a controlled
multimodal benchmark for robotic perception under severe rain, snow, dust, fog, and darkness, with registered RGB, depth, and infrared observations, clean references, and grounded high-level perception tasks. We further develop Fusion-to-RGB, with two parameter-efficient sensor-fusion realizations based on
token-space fusion for a
diffusion transformer and residual latent conditioning for an inpainting UNet. Across frozen open-vocabulary grounding and
vision-
language models, RGB+D+IR fusion improves all paired downstream comparisons over the corresponding RGB-only restorers, including AP50 gains across all ten detector comparisons. Importantly, these perception gains do not consistently follow conventional image-fidelity metrics, and increasing weather severity does not induce monotonic downstream degradation. These results show that complementary sensing can preserve reusable robotic perception under extreme conditions, while highlighting task-level perception robustness as an objective distinct from visual restoration quality.
Read the full abstract ▾
All authors Fucai Ke, Sukai Huang, Junyi Hao, Kal Backman, Naim Rastgoo, Gholamreza Haffari, Hamid Rezatofighi
Information Theory
WZIP and WLZ4: LZ77 Codecs with Match-Length-Dependent Sliding Windows
Yingquan "Cody" Wu
An LZ77 codec bounds every match by one sliding window, trading cheap offsets for short matches against reach for long ones. Match-length-dependent windows refine this trade-off: each match length has its own window, and the decoder infers the offset range from the decoded length. We present two such codecs: WLZ4, a byte-aligned LZ4-class format with one-byte and flagged offsets, and WZIP, an
entropy-coded Zstandard-class format. Each block begins with its decoded length, from which WZIP derives its widest window and a decoder sizes its output. LZ4 blocks may expand incompressible input by 0.4%; WLZ4 adds at most 15 bytes, WZIP 2. We describe the formats, threaded match finders, decoders and parser. On Silesia, WLZ4 reaches a ratio up to 16% above LZ4HC's, decoding more slowly, and WZIP exceeds Zstandard 22's ratio while its trusted decoder runs at 91% of Zstandard's speed (87% checked; on enwik9, about as fast).
Read the full abstract ▾
Sound
Two-Stage Multi-modal Learning for Dynamic Audio-Visual Navigation: From Physical Alignment to Scene Aggregation
Jia Li and Yinfeng Yu
Embodied Audio-Visual Navigation (AVN) requires an
agent to locate sound targets by jointly leveraging visual and auditory cues. While prior work has achieved notable success with static sound sources, real-world scenarios often involve moving targets, giving rise to the more challenging problem of Dynamic Audio-Visual Navigation (D-AVN). Existing approaches largely rely on semantic auditory features, which limits generalization to unheard sound categories and hinders fine-grained spatial
reasoning. To address these challenges, we propose a novel Two-Stage Multi-modal Learning framework for D-AVN. In the Physical
Alignment stage, the proposed Intensity-Calibrated Geometry Encoder (ICGE) performs physics-informed
alignment of sound intensity with visual geometry to capture category-agnostic spatial correspondence. In the Scene Aggregation stage, a
Transformer-based Cross-Modal Scene Aggregator (CMSA) dynamically integrates multi-modal features to construct a robust state representation for policy learning. Extensive experiments on Replica and Matterport3D demonstrate that our method achieves state-of-the-art success rates, while significantly improving generalization and navigation efficiency in complex environments and under unheard sound scenarios.
Read the full abstract ▾
Robotics
Assessing the Marginal Utility of Exocentric Head Views in UMI-Style Large-FoV Wrist-Camera Manipulation
Yuhui Duan, Shi Jin, Yuntian Wang et al. (+5 more)
Multi-view perception is often treated as a safe design choice for
robot manipulation: if one camera is useful, more cameras should be better. We revisit that assumption in tabletop bimanual manipulation by comparing policies trained with two large-field-of-view (FoV) wrist cameras against policies that additionally receive a head view, using controlled-variable experiments on a real bimanual platform. Across three tabletop tasks, adding a head view does not consistently improve task completion or execution quality: when the wrist cameras already observe the objects, grippers, and goal regions, wrist-only policies form a strong baseline. Restricting the wrist-camera FoV increases the potential value of a head view, but performance improves most reliably when the added view supplies concentrated, task-relevant information: region-of-interest (ROI) cropping yields more consistent head-view gains than the uncropped image, which is dominated by background and task-irrelevant regions. The data-scaling results further suggest an interaction between FoV and demonstration count: wide observations improve coverage but may require more data to stabilize, and they may reach a higher performance ceiling once enough demonstrations are available. These results suggest that camera design should be framed as a task-relevance and information-density problem rather than as a simple count of input views.
Read the full abstract ▾
All authors Yuhui Duan, Shi Jin, Yuntian Wang, Jin Wang, Siao Liu, Wenchang Gao, Zhaxizhuoma, Yan Ding
Machine Learning
One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns
Yiyang Fu, Zihao Huang, Dongchen Han et al. (+4 more)
Large
language models typically support different inference budgets through separate model sizes or fixed compute configurations. In multi-turn interactions, however, compute demand can vary substantially across turns. Using a high-compute model for every turn wastes computation, while routing among independent models may require rebuilding model-specific history states after switches. We therefore ask whether a single shared model can support multiple compute budgets that can be flexibly assigned across turns. We introduce Multi-Ratio ConceptMoE, which jointly supports
token-to-concept compression ratios of 2, 4, and 8 (CR2/CR4/CR8) within a shared backbone. Lightweight full-
token modules reduce compression-independent cost, ratio-specific boundary routers support distinct compression levels, and cross-ratio training enables mixed-ratio processing within the same context. Across PTBench and SFTBench, the three fixed modes outperform their compute-matched MoE baselines in all 6 comparisons while remaining competitive with independently trained fixed-ratio specialists. On CodeChat and CoSQL, mixed-ratio inference improves the accuracy–compute trade-off, outperforming the Large MoE by 5.87 and 2.68 percentage points while reducing FLOPs by 41.1% and 12.3%, respectively. Under the same turn-wise budget schedule, Multi-Ratio ConceptMoE further reduces FLOPs by 78.4% and 46.9% relative to routing among independent models. These results demonstrate that a single shared model can provide multiple compute budgets for flexible compute allocation across turns.
Read the full abstract ▾
All authors Yiyang Fu, Zihao Huang, Dongchen Han, Shukai Gong, Zhen Dong, Qiyang Min, Daquan Zhou
Computation and Language
Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning
Yongyi Huang, Huaping Zhang, Wenyao Cui et al. (+3 more)
Large
language models (LLMs) remain unreliable when
reasoning about the future. Existing models often overlook the difference among future states, committing to specific answers even when the queried facts are inherently volatile. To capture this challenge, we introduce ChronoRegime, a future-oriented temporal
reasoning task that requires models to determine whether historical temporal evidence justifies commitment to a future answer. Furthermore, we propose Confidence-Aware Temporal
Reasoning (CTR), a framework that estimates future predictability from temporal dynamics and regulates answer commitment accordingly. Rather than performing unconditional forecasting, CTR commits only when the reconstructed evidence supports the target future state. Across multiple LLMs, CTR improves strict overall accuracy by 6.7 percentage points and reduces
hallucination rates by 18.4 percentage points on average over the plain QA baseline. These results demonstrate that explicit predictability assessment is an effective mechanism for safer and more reliable temporal
reasoning under future uncertainty.
Read the full abstract ▾
All authors Yongyi Huang, Huaping Zhang, Wenyao Cui, Qiuchi Li, Lei Li, Baohua Zhang
Robotics
LeWAM: End-to-End World and Action Modeling with JEPAs
Minghao Fu, Tavis Siebert, Eryk Halicki et al. (+1 more)
Joint-
embedding predictive architectures (JEPAs) learn compact latent world models without pixel reconstruction. Existing JEPA pipelines typically train visual representations and action-conditioned dynamics before adding a control policy or solver. We introduce LeWAM, an end-to-end JEPA for control with: (1) a joint training objective over next latent state prediction and action flow matching, and (2) an isotropic Gaussian constraint on the latent state, enabling a single model to support direct policy execution and efficient planning by evaluating sampled actions with its learned latent dynamics. Compared with prior JEPAs in visual planning, LeWAM improves success rate from 28.6% to 89.7% on contact-rich tasks and from 10.9% to 46.2% on long-horizon tasks, and plans 32.3 times faster. On behavior cloning tasks in simulation and physical
robots, LeWAM is also competitive with established methods. Interpretability analyses show that LeWAM learns control-relevant representations and action distributions effectively guiding test-time planning and control.
Read the full abstract ▾
All authors Minghao Fu, Tavis Siebert, Eryk Halicki, Randall Balestriero
Machine Learning
Deploying RDMA for Distributed Inference and Training At Scale
Yibo Huang, Yi Cui, Yukai Huang et al. (+12 more)
RDMA can reduce communication overhead in distributed machine learning systems, but realizing these benefits in production requires more than replacing TCP. Variable-size messages, concurrent connections, bursty incasts, and service failures introduce challenges that hardware offload alone cannot address. This paper reports our experience deploying ByteExpress, a software communication layer over hardware RDMA, in ByteDance's parameter-server-based inference and training systems. We present three lessons from the deployment: efficient RDMA requires buffer management across application and transport layers; scalable communication requires coordinated management of connections, receive capacity, and outstanding data; and service availability requires recovery above the transport layer. ByteExpress combines an RDMA-aware allocator, zero-copy transfers, QP multiplexing, receive-credit flow control, a software send window, and RPC-assisted recovery. In production inference, ByteExpress reduces mean and P99 model parameter fetch latency by 35.7% and 43.7%, respectively, and total CPU usage by 10.69% compared with kernel TCP. In training, ByteExpress reduces P99 model parameter push latency by up to 74.0% compared with TCP, with no PFC pauses observed at runtime.
Read the full abstract ▾
All authors Yibo Huang, Yi Cui, Yukai Huang, Huaping Zhou, Jiancong Tong, Zhaoyu Wu, Gen Miao, Haoran Wei, Boyan Ding, Zhuo Jiang, Jianxi Ye, Yibo Zhu, Chuanxiong Guo, Yang Xu, Jie Wu
Artificial Intelligence
VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails
Duy Nguyen, Lesly Miculicich, Bhavana Dalvi Mishra et al. (+5 more)
LLM
agents increasingly operate over sensitive resources, such as private documents and mutable system states, which can create serious safety and security risks. Runtime guardrails should therefore make inspectable, reproducible, and deterministic allow or refuse decisions before potentially irreversible
agent actions are executed. However, safety and security requirements are rarely complete before deployment, so guardrails need to keep adapting as new risks emerge. Existing adaptive guardrails learn from deployment experience, but they usually apply safety policies through LLM inference, which can lead to inconsistent decisions and ambiguous policy interpretations. Formal guardrails, on the other hand, enforce policies deterministically, but they usually rely on pre-deployment or task-specific policies and have no mechanism to adapt to newly observed risks. We introduce VEPA, a framework for the verified
evolution of formal
agent guardrails. VEPA represents the guardrail as a formal policy of executable symbolic rules over typed
agent events. During deployment, we use an LLM guided by deployment feedback to propose policy patches that fix newly observed failures while preserving previously correct behavior. Then, a deterministic verifier only accepts policies that are structurally valid and conflict-free. Finally, an evidence-aware authority layer activates a verified rule only when it has enough supporting evidence, so uncertain updates cannot directly affect guardrail decisions. Across ASSEBench-Safety, ASSEBench-Security, and ATBench, VEPA consistently outperforms baselines while expanding the scope of deterministic formal-policy enforcement. These gains also hold under more challenging deployment conditions, including mixed streams, corrupted feedback, and longer horizons.
Read the full abstract ▾
All authors Duy Nguyen, Lesly Miculicich, Bhavana Dalvi Mishra, Shuo Li, Krishnamurthy Dj Dvijotham, Mohit Bansal, Tomas Pfister, Long T. Le
Computer Vision
Spend Where It Matters: Particle Search with MH Refinement for Budget-Constrained Audio-Visual Alignment
Shivanshu Shekhar, Raghavendra Addanki, Tong Zhang et al. (+1 more)
Reward-guided inference-time
alignment can improve joint audio-visual generation, but optimizing multiple
alignment objectives requires many expensive model evaluations, making existing methods costly under limited compute. Particle-based search enables global exploration but incurs estimation error with a finite population, while Metropolis-Hastings (MH) can refine candidates locally but benefits from a strong initialization. We introduce Spend Where It Matters (\modelname), a two-stage, training-free, reward-agnostic framework that combines particle search with MH refinement under a fixed compute budget. In the first stage, we adaptively allocate particles across denoising checkpoints using online variance estimates, minimizing estimation variance while concentrating compute where it is most useful. This search provides a promising candidate for MH refinement, which uses local noise-and-denoise proposals on completed outputs to further improve reward. By starting from a strong candidate, MH can recover additional reward without requiring a larger particle population or costly global exploration. We show that, at matched compute, combining particle search with MH refinement achieves higher rewards than either approach alone. On JavisBench-Mini, at closely matched compute, \modelname achieves mean relative gains across seven metrics of $30.7\%$ over BoN and $14.1\%$ over EvoSearch with JavisDiT++, and $9.2\%$ over BoN and $17.0\%$ over EvoSearch with LTX-2. Beyond joint audio-visual generation, we also demonstrate the benefits of adaptive particle allocation on SD1.5 image generation, improving AestheticScore by $2.2\%$ and ImageReward by $6.0\%$ over uniform allocation.
Read the full abstract ▾
All authors Shivanshu Shekhar, Raghavendra Addanki, Tong Zhang, Uttaran Bhattacharya
Machine Learning
The Expressive Power of Random-Feature MPNNs Across Graph Sizes
Robert R. Nerem, Mitchell Black, Antonis Vasileiou et al. (+2 more)
Continuous random node features increase the expressivity of message-passing neural networks (MPNNs), but existing theoretical analyses are not fine-grained enough to capture their limitations, particularly in approximating functions across graph sizes or under a fixed number of random bits. We develop a population-level framework for size-uniform approximation. For MPNNs with a graph-size-independent Lipschitz bound in their initial features, including standard mean, max, and order-normalized sum architectures, we show that continuous random features can be quantized to finitely many colors with arbitrarily small uniform error in expected output. This reduction lets us transfer limitations on finite-color distinguishability to limitations on size-uniform approximation with continuous random features. We use this framework to prove that these MPNNs are not size-uniformly universal, analyze the expressivity gains from colors and independent trials, and establish incomparability between random-color MPNNs and higher-order Weisfeiler-Leman methods. We also give finite-color MPNN constructions for tree subgraph isomorphism via color coding and a local MST task.
Read the full abstract ▾
All authors Robert R. Nerem, Mitchell Black, Antonis Vasileiou, Christopher Morris, Yusu Wang
Machine Learning · Cross-listed from quant-ph
Trainable Quantum-Native Language Models: Dissipative Memory, Capacity Limits, and Hardware Validation
Deniz Yunus Göğüş
We study byte-level autoregressive
language models whose hidden state is a small
quantum register, whose transitions are learned
token-conditioned
quantum channels, and whose next-byte probabilities come directly from Born-rule measurements without a learned classical vocabulary projection or softmax. In the fixed-width recurrent setting,
unitary dynamics cannot contract or reset stored distinctions; experimentally,
unitary recurrence loses to its retrained one-
token control in every tested variant. Introducing learned dissipation, then
token-conditioned dissipative gating, yields useful
memory beyond one
token. The gated model improves test negative log-likelihood by 0.20 +/- 0.03 nats/byte over retrained parameter-matched one-
token controls at context length 12, and by 0.29-0.33 at longer contexts, but never beats retrained two-
token controls. A key-value recall
benchmark shows a width-dependent threshold: one stored pair meets the pre-registered accuracy bar at 4-5
memory qubits, two pairs at 6-7, and three pairs remain unsolved. This is consistent with, but does not establish, a capacity explanation for the short effective
memory horizon. As a secondary result, one-
qubit models reach lower stationary
memory entropy than a heuristically optimized classical predictive frontier at matched error in 9/9 seeds. On IBM Heron hardware, computational-basis
memory-register distributions show signal against a uniform null in 12/12
circuits across prefixes of up to 12
tokens, next-bit probabilities pass pre-registered accuracy bars at four-
token prefixes, and bytes are generated autoregressively by sampling physically measured bit probabilities. The tested models are classically simulable and substantially worse than classical n-gram baselines. We claim no computational
quantum advantage.
Read the full abstract ▾
Computational Complexity
The Complexity of Finding Additional Solutions
Saman Farhat
We study the difficulty of finding a new solution when a list of distinct solutions is already supplied. For any fixed finite collection of list lengths, we can prescribe the additional-solution degrees while preserving a given $1$-paddable domain and first-solution degree. We also prove an exact compatibility condition for prescribing an arbitrary positive-list degree at the same time: it must dominate every prescribed fixed-level degree, and this condition suffices. All degrees use
polynomial-time reductions with at most one oracle query and correct behavior on empty fibers; the realization needs no assumption about P versus NP. The combined construction gives each underlying witness exponentially many short counter copies. A list that exhausts these copies is long enough to pay for exhaustive search through the underlying witness bound. Separately, we construct a total problem whose first-solution task and every fixed-length additional-solution task are
polynomial-time solvable, while its arbitrary-list task is FNP-complete. Assuming P differs from NP, the domain, first degree, and entire fixed-level degree sequence therefore do not determine the arbitrary-list degree. A constant fiber cap restores determination by finitely many fixed levels. The constructions change witness sets and do not prescribe an infinite sequence of degrees or enumerate all remaining solutions.
Read the full abstract ▾
Computation and Language
People Making Conversation: Evaluating How Naturally Speech Models Converse
Arya Bastani and Iman Modarressi
A conversational
speech model has to decide, at every pause, whether to speak. Existing evaluations test boundary detection, policy adherence, or aggregate statistics, not this decision. We place real-time
speech systems at 427 pauses and 482 turn ends from 176 unscripted conversations in Seamless Interaction, give each the conversation so far, and score what it generates against what the person did: whether and how soon it speaks at a pause; its latency, length, and wording at a turn end; and whether it can answer a question about the preceding 30 to 120 seconds. Across six systems, the hosted APIs (GPT Realtime, Gemini 3.1 Flash Live, Grok Voice) respond at almost every pause whichever endpointer they use; only their latency, about 1 to 4 s with silence-based endpointers and about 8 s with semantic turn detection, decides whether the words land inside the pause. The full-duplex models (PersonaPlex, Moshi) are the only systems that regularly stay silent and the only ones that interrupt within a human reaction time. Hosted systems reply longer than the person. Given the history as text, hosted systems recall 41 to 60% of conversation facts under a Claude Opus 5.5 judge and 19 to 26% under a strict word matcher; hearing it as audio, full-duplex models recall 17 to 22% and 12 to 15%. We release the labels, points, harness, and every output.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.comp-ph
Polyconvex neural-network surrogates with learned paired directional features for anisotropic hyperelastic homogenization
S. Ares de Parga, A. Cornejo, J. A. Hernández et al. (+1 more)
Approximating the effective anisotropic hyperelastic response of a representative volume element (RVE) requires constitutive expressiveness, mechanical consistency, and computational efficiency. This work develops a polyconvex physics-augmented neural network (PANN) construction based on paired directional features whose orientations, stretch powers, and determinant exponents adapt to the RVE response. The features are composed with convex, componentwise nondecreasing cores, realized as an input-convex neural network (ICNN) or an input-convex Kolmogorov-Arnold network (ICKAN). The complete energies satisfy objectivity, an exactly stress-free reference, two-dimensional polyconvexity, and prescribed growth conditions by construction, and nonnegative energy is certified separately for the selected models. On a multicavity and a single-cavity periodic
cell, these energies are compared with an Unconstrained energy, trained identically without the
curvature and growth constraints, and with three hyperreduced projection-based reduced-order models (HPROMs), which serve as physics-based references. On the first
cell, learning the features lowers the stress error sevenfold, and six features suffice on both. The constrained energies remain below one percent in stress error and in the displacement error of a tensile-coupon FE$^2$ application with a full-order reference, whereas the Unconstrained energy and the HPROMs are more accurate inside the data. Beyond the data, however, the Unconstrained energy loses rank-one convexity, and under confined compression it stops below half of the 500 MPa that the constrained energies reach. These results quantify what the guarantees cost in accuracy and what they secure beyond the data.
Read the full abstract ▾
All authors S. Ares de Parga, A. Cornejo, J. A. Hernández, R. Rossi
Sound
Efficient Audio-Visual Speech Enhancement via Reinforcement Learning-Based Neural Architecture Search
Khubaib Ahmed, Ahsan Adeel, Nasir Saleem et al. (+3 more)
Audio-visual
speech enhancement (AVSE) improves
speech intelligibility in noisy environments but often relies on computationally expensive models unsuitable for resource-constrained edge devices. This paper introduces a reinforcement learning-driven neural architecture search (RL-NAS) framework to discover compact, efficient AVSE architectures. The search space preserves temporal
alignment between audio and visual streams, while a novel reward function jointly optimises
speech enhancement performance, measured by SI-SNR improvement, and model compactness. Using proximal policy optimisation with constraint-aware action masking, the framework evaluates only 35 candidate architectures and identifies a model with 2.9 million parameters, compared with 22 million in the baseline. The proposed architecture achieves a 14.5 dB SI-SNR improvement, only 0.7 dB below the baseline, while reducing model size by approximately nine-fold. Evaluation on commercial mobile CPUs demonstrates a 4.3-fold reduction in real-time factor, supporting practical on-device deployment. Compared with random search, RL-NAS achieves 92% higher search efficiency. Architectural analysis reveals that shallower but wider temporal convolutional blocks and aggressive visual pathway
pruning can maintain enhancement performance while substantially reducing computational requirements. These findings demonstrate the potential of reinforcement learning-guided architecture search for developing lightweight, efficient and deployable
multimodal speech enhancement systems.
Read the full abstract ▾
All authors Khubaib Ahmed, Ahsan Adeel, Nasir Saleem, Kia Dashtipour, Ahsan Ulhaq, Amir Hussain