Computer Vision
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
All of arXiv
Sunday 8 November
This paper proposes Graphene, a lightweight image super-resolution architecture with two complementary feature refinement mechanisms: Ising-model-inspired local feature refinement using an Ising Refinement Block (IRB) and stage-history-based feature refinement using a History Attention (HistAttn) module. The IRB reuses attention output features and pre-softmax attention logits to construct signed pairwise token couplings within each local window, applies unrolled mean-field updates, and refines features through a gated residual correction. These signed couplings allow alignment and opposition between latent spins to modulate local feature refinement. HistAttn attends over the current stage output and earlier representations at the same token position and adaptively blends the current stage output with a history-weighted feature aggregate without adding spatial pairwise attention. On Urban100 at $\times4$, Graphene and Graphene-light improve over IET and IET-light by 0.24 dB and 0.38 dB, respectively, with 34.3%/13.7% fewer parameters, 44.8%/44.4% fewer FLOPs, 83.9%/95.9% lower latency, and 63.7%/92.0% lower peak memory. Real-world SR comparisons further show that Graphene recovers fine details and preserves textures across diverse degradations. Code and reference checkpoints are available at https://github.com/skethz/Graphene
Soft Condensed Matter
Odd Darcy Law: Odd Viscosity and Edge Currents in Porous Media
We derive and numerically validate an odd Darcy law for chiral active fluids in porous media, in which an antisymmetric permeability tensor induces a flow transverse to the applied pressure gradient. We identify two distinct mechanisms leading to this odd response: odd viscosity in the fluid or the nonlinear coupling of edge currents to inertia. We then show how the transverse transport depends on porosity, boundary friction, and chirality.
Read the full abstract
Sound
GlobalTap: Globally Diverse Beat Tracking Benchmark via Crowdsourced Tapping
Existing beat-tracking benchmarks draw from a narrow range of musical cultures, predominantly Western, and are difficult to scale due to reliance on expert annotation. We address both limits with GlobalTap, a benchmark of 200 popular-music excerpts spanning 59 countries, annotated by 746 participants recruited across ten countries. The benchmark is created using a scalable online tapping pipeline that records taps via audio for high temporal precision, aggregates pooled tap times into consensus beat annotations, and computes intrinsic quality measures that flag perceptually difficult excerpts without requiring a reference. In a separate study on a different 240-excerpt validation set, tapped by an additional 733 participants, an independent group of 130 listeners rated how well the resulting beat tracks lined up with the music, and we detected no overall difference between our annotations and existing reference annotations. Crowd-derived annotations occasionally diverged from the references in phase and metrical interpretation, yet listeners did not consistently prefer the reference versions, suggesting that crowd-derived and existing reference annotations can reflect different perceptual or structural interpretations. The disagreements were often systematic rather than random, and metrical-level choices differed across the ten recruitment countries. We release GlobalTap together with open-source pipeline code as a listener-derived resource for evaluating beat-tracking systems on culturally diverse music.
Read the full abstract
Computer Vision
From Game Generation to Game Playing: Fully Automated Ability Training for Vision-Language-Action Models
Training vision-language-action (VLA) models to follow gameplay instructions across diverse games is limited by the cost of collecting demonstrations. We introduce a framework that automatically generates game environments and expert demonstrations. An LLM-powered agent uses game-building tools to construct executable environments and tasks targeting specified skills. Programmatic experts then use privileged simulator state to generate aligned instructions, rendered observations, and keyboard and mouse actions. We train our game policy, Script2Play, by post-training a 4B vision-language model with behavior cloning on 150.3 hours of synthetic gameplay in Minecraft and Roblox, without human gameplay demonstrations or reinforcement learning. Evaluation on multiple public game benchmarks demonstrates that Script2Play follows gameplay instructions effectively and generalizes across game engines, highlighting the effectiveness of targeted synthetic supervision.
Read the full abstract
Representation Theory
The Fourier kernel and invariant trace formula of $\rm{GL}(3)$
Trace formula is an important method to study the Langlands program. Arthur obtains the existence of stable trace formula for connected reductive group. In this paper, we will give the explicit invariant trace formula of GL(3). For general reductive groups, Arthur gave an inductive proof of the existence of the invariant trace formula and provided explicit examples for GL(2). For GL(3), we successively compute the invariant distributions, give all the Fourier kernels for the GL(2) cases, and finally obtain the concrete invariant trace formula.
Read the full abstract
Probability
Stochastic Parallel Transport along Markov Processes: I. General Theory
We give a framework for transporting vectors along Markov processes that may have jumps, without assuming a manifold or other specific geometric structure. We prove existence and uniqueness of the resulting transport. In doing so, we develop a theory of vector bundles defined quasi-everywhere, in which the vectors live, and an axiomatic framework for energy forms that determine the bundle and the transport.
Read the full abstract
Data Structures and Algorithms
Online Correlated Exponential Clocks
In online resource allocation, we seek to allocate an incoming sequence of requests $j \in J$ among a set of offline resources $i \in I$, where decisions must be made immediately without knowledge of the future. State-of-the-art results typically follow from relax-and-round methods. For many problems, recent advances have come from improved methods of online rounding with negative correlations. However, such rounding schemes have largely been implemented on a case-by-case basis, making it difficult to transfer improvements and new ideas between problem settings. This leads us to ask the question: Can we develop unified methods of online rounding with negative correlations which can obtain state-of-the-art guarantees across different resource allocation settings? We answer this question affirmatively by introducing the framework of Online Correlated Exponential Clocks (OCEC). In this framework, fractional allocations $x_{ij}$ are assigned exponential clocks $Y_{ij} \sim \mathrm{Exp}(x_{ij})$, and each request $j$ is allocated to the resource $i$ with smallest $Y_{ij}$. The key idea is that the sequence $(Y_{ij})_j$ for each fixed $i$ is negatively correlated via an OCEC generator, resulting in better-than-baseline guarantees. Our contributions are two-fold: First, we introduce OCEC rounding as a problem-independent interface which any online algorithm can use. This isolates the challenge of online rounding into the self-contained problem of designing an effective OCEC generator. Second, we demonstrate the flexibility of this method by giving a single OCEC generator which yields improved competitive bounds in three distinct problems: 0.556 for Display Ads, 0.530 for AdWords, and 4.69 for squared-load balancing. Previous best results were obtained by Blanc and Charikar (FOCS 2021), Chen, Huang, and Sun (FOCS 2024), and Borst and Kashaev (SODA 2027), respectively.
Read the full abstract
Networking
Confidence-driven adaptive semantic transmission for task-oriented communication
Image-based remote monitoring over wireless networks faces a trade-off between communication cost and classification reliability. Transmitting complete images is communication-intensive, whereas relying solely on lightweight edge classifiers may compromise accuracy. To address this challenge, we propose Confidence-Driven Adaptation (CDA) for image transmission and classification. An edge device (ED) captures images and applies a lightweight classifier before transmission to a remote server. Based on its classification confidence, the ED selects among three transmission modes with varying levels of information: a short text string reporting its predicted class when confidence is high, a compressed Region of Interest (ROI) at intermediate confidence levels, or an uncompressed ROI when confidence is low. The server accepts the predicted class directly in the first case and performs classification using a more powerful classifier in the other two cases. Numerical evaluations under bandwidth-limited, lossy links and latency-constrained settings demonstrate that CDA achieves high task accuracy at the receiver compared with non-adaptive baselines that transmit only the edge-classifier outcome or the uncompressed ROI.
Read the full abstract
Computer Vision
CrossLiDAR: Controllable Multi-Sensor LiDAR Sequence Generation
High-fidelity LiDAR simulation remains a bottleneck for scalable development and validation of autonomous systems. Existing generators can synthesize realistic scans, but they are typically constrained to a single sensor configuration, offer limited control over structure and geometry, and drift in long-horizon 4D generation. We present CrossLiDAR, a unified transformer-based framework capable of generating controllable and spatio-temporally consistent multi-sensor LiDAR sequences. Our approach leverages a rectified flow objective with a Multi-Modal Diffusion Transformer (MM-DiT) backbone, within a compact latent space of range images. To support multiple LiDAR sensors, an Inter-sensor Module enables interaction across sensors, while a ControlNet-style branch provides structural conditioning (e.g., BEV priors or 3D bounding boxes). For modeling the temporal consistency, CrossLiDAR generates short $N$-frame sequences and extends them autoregressively to improve long-horizon coherence. Our model significantly outperforms state-of-the-art baselines, achieving an average improvement of 29.56% in JSD and 15.36% in MMD evaluated on nuScenes and the Waymo Dataset. CrossLiDAR bridges the gap to modern autonomous-driving simulation by enabling calibration-consistent multi-sensor LiDAR rollouts over long horizons for controllable, scenario-based testing.
Read the full abstract
Audio and Speech Processing
Virtual-Flow: Virtual Microphone-based Speech Enhancement via Semi-supervised Flow Matching
Neural network-based virtual microphone estimation (neural-VME) synthesizes microphone signals at unobserved spatial locations from a limited set of real microphone (RM) physical recordings. This enables high-resolution arrays that improve spatial processing for downstream tasks such as speech enhancement. However, existing methods rely on supervised training with ground-truth signals captured at virtual locations, requiring datasets that scale with the number of virtual microphones (VM) and leaving open the question of how to design optimal large-array configurations. We propose Virtual-Flow, a flow-matching framework that implicitly generates VM signals conditioned on real recordings, without requiring ground-truth VM signals. We introduce a semi-supervised training strategy based on pseudo-VM targets constructed from time-delayed superpositions of real recordings. Virtual-Flow shows improved magnitude estimation in high-frequency bands, yielding richer spatial cues for beamforming. Experiments demonstrate that the proposed Virtual-Flow, combined with reflow distillation, outperforms existing neural-VME baselines in VM-based beamforming and achieves competitive end-to-end speech enhancement performance with low computational cost.
Read the full abstract
Numerical Analysis
On-the-Fly Reduced Bases Through the Lens of Augmented Krylov Methods
On-the-fly reduced order models (ROMs) are widely used in applications where multiple queries of large-scale models are required in an iterative method, like PDE-constrained optimization or fluid-structure interaction. When compared to classical offline–online ROMs, they have the advantage of being agnostic to any precomputed training data, mesh or geometry, which makes them more general linear/nonlinear solver accelerators. The main goal of this work is to study the effect of using a reduced basis constructed on-the-fly to accelerate a restarted Krylov algorithm, and to formally bridge this category of data-driven methods with classical augmented Krylov methods. The guiding principles of on-the-fly reduced basis will be translated into the framework of Krylov subspace methods, for a Petrov-Galerkin projection method. Previous corrections generated by the algorithm are stored in a snapshot matrix, and a singular value decomposition (SVD) is used to determine a reduced subspace containing the most significant directions. It will be shown that this approach can be embedded in the framework of Krylov methods with augmented or deflated restart, but with a different, data-driven recycling strategy. An analytical study will be presented to determine the consequences of augmentation by ROM-based vectors. Numerical experiments on a convection-diffusion problem with various degrees of convection will show that the proposed methodology yields results comparable to classical iterative linear solvers in some regimes, especially for nearly symmetric or skew-symmetric operators. At equal sizes of the augmentation basis, the convergence was sometimes faster with the proposed framework than with deflation methods.
Read the full abstract
Combinatorics
Triangle-overlap cores and density bounds for Tuza's conjecture
For a finite simple graph $G$, let $\nu(G)$ be the maximum number of edge-disjoint triangles and let $\tau(G)$ be the minimum number of edges meeting every triangle. We prove $\tau(G)\le2\nu(G)$ when each edge belongs to at most four triangles, the edges belonging to four triangles form components with at most two edges, and the maximum average degree is at most $25/2$. No upper bound on maximum vertex degree is imposed. We also localize the density condition. Let $K$ be the Hifumi core, defined as the vertex set of the 4-core of the spanning subgraph formed by edges belonging to at least three triangles. It suffices to impose the density condition on $G[K]$, including all original edges between vertices of $K$. More generally, when the four-triangle edges have maximum degree at most two, reductions produce a subgraph $R\subseteq G[K]$ with $\tau(G)-2\nu(G)\le\tau(R)-2\nu(R)$. Consequently an empty core gives a density-free sufficient condition. For the first graph class, a quantitative surplus argument strengthens both the global and localized density conditions to the strict bound $25/2+2/56775$. The proof combines edge reductions, discharging, finite certificates and a weak König–Egerváry lemma for links of arbitrary order. The general conjecture and the removal of the density condition from the first graph class remain unresolved here.
Read the full abstract
Robotics
From Festival Video to the Stage: A Sim-to-Real Ladder for Long-Horizon Expressive Whole-Body Dance on a Commercial Humanoid
We present a pipeline for transferring Awa Odori, a traditional Japanese festival dance, from monocular video to a commercial Unitree G1 EDU humanoid. The pipeline combines human mesh recovery, kinematic retargeting, reinforcement learning for motion tracking in simulation, and onboard deployment via ONNX. Training ran on a single RTX 5070 GPU. An eleven-version deployment ladder evaluated on hardware examines three interventions. We detect and repair silent corruption of deployment artifacts, model state-estimator drift during training, and edit the reference motion to support stable execution and a controlled ending. The final policies achieved three consecutive rope-free completions of a 43-second routine, a 46-second performance with automatic handoff, and a continuous 9.7-minute rope-free performance composed from the captured motion. In a live handover, a single remote request let the robot start from and return to the manufacturer's walking controller on stage, with a measured torque-free window of 45-140 ms. We report the training dynamics and hardware outcomes and discuss failure boundaries involving compliant flooring and occlusion in monocular capture.
Read the full abstract
Combinatorics
Lower bound on the size of splitting systems
For even $t$ and an $n$-set $X$, an $(n,t)$-splitting system is a family ${\mathbb{B}} \subseteq 2^X$ with the property that for each subset $Y \in {X \choose t}$, there exists $B \in \mathbb{B}$ such that $|B \cap Y| = t/2$. The problem of interest is to determine the minimum size of such splitting systems. We show that any $(n,t)$-splitting system has size at least of order $t$, improving the previous lower bound of $\sqrt t$ while the best known upper bound is of order $t^{3/2}$.
Read the full abstract
Computation and Language
LongCap: Hour-Scale Timestamped Audio Captioning via Chunk-wise Processing
Describing hours of audio requires accurate event timing and sustained descriptive detail throughout the recording. We present LongCap, a framework for timestamped audio captioning (TAC), with the human-annotated LongCapBench and three diarization-inspired metrics: Timeline Error Rate (TER), Granularity Error Rate (GER), and Caption Similarity (tcpCapSim). LongCap interleaves audio chunks with structured event captions, using relative timestamps and retained context to support length extrapolation within a 1M-token inference context window. Event-level reannotation restores caption detail, while systematic studies examine model scaling, dependency supervision, and self-distillation. LongCap-Diar achieves strong benchmark results and extrapolates to 16 hours of concatenated audio despite training on recordings no longer than 40 minutes. Our TAC models are competitive with Qwen3.5-Omni-Plus on short clips, outperform evaluated baselines in caption similarity and timeline accuracy in segment-level comparisons on LongCapBench-TAC-Long, and caption full recordings approaching two hours. On LongCapBench-TAC, 9B and 35B-A3B offer favorable size-performance tradeoffs, while 122B-A10B substantially improves event-dependency recovery. These findings support long-horizon general audio understanding and provide a foundation for always-on voice agents.
Read the full abstract
Data Structures and Algorithms
Optimal Polynomial-Query Approximation for Consistent Submodular Maximization with Short Lookahead
Elements arrive one at a time, and after each arrival an algorithm holds a set of at most $k$ arrived elements. Its goal is a held set whose value under a monotone submodular function is close to the best value that $k$ arrived elements can achieve. The recourse of an update is the number of elements inserted into or removed from the held set, and we require it to be bounded independently of $k$ and of the number $n$ of arrivals. With evaluations only on sets of arrived elements and polynomially many of them, the best ratio a randomized algorithm can achieve is $2-\sqrt{2}\approx0.5858$. We show that seeing future arrivals raises the best ratio for polynomially many evaluations to $1-1/e\approx0.6321$, for deterministic and for randomized algorithms; no algorithm with polynomially many evaluations exceeds $1-1/e$, even when all elements are available at once. For every $\varepsilon>0$, a deterministic algorithm that sees the next $\lceil\varepsilon k/3\rceil$ arrivals keeps a set of value at least $1-1/e-\varepsilon$ times the optimum at every time, changes $O(\varepsilon^{-3})$ elements per arrival and makes $(n+1)^{O(\varepsilon^{-2})}$ evaluations. With the whole arrival sequence known in advance, a deterministic algorithm attains the same ratio with $O(\varepsilon^{-2})$ changes per arrival. A randomized algorithm with the same short lookahead makes $O(n^2k)$ evaluations, changes $O(\varepsilon^{-2})$ elements per arrival, and attains the same ratio in expectation at each fixed time. The main tool is a greedy algorithm with an explicit guarantee for each of its partial solutions combined with each initial segment of the known future arrivals. A second tool moves between two such solutions one element at a time while keeping the value high, and the deterministic algorithm times each move using upper bounds on the optimum from failed searches.
Read the full abstract
Robotics
HARP-Bench: Benchmarking Robot Manipulation Around Active Humans
Recent robot manipulation benchmarks have enabled systematic evaluation of general-purpose robot policies across diverse objects, scenes, instructions, and embodiments. However, most existing benchmarks still assume that the robot is the only active agent and that task semantics are determined primarily by the instruction and object state. This assumption overlooks a common source of real-world variation: humans actively sharing the workspace. In such settings, humans may reveal an implicit goal, complete part of the task, temporarily change object availability, or constrain safe robot motion while working nearby. We introduce HARP-Bench, a benchmark for evaluating robot manipulation policies in workspaces shared with active humans. HARP-Bench treats human activity as part of the manipulation problem, rather than as background scene variation. It organizes human-present manipulation into four conditions: Cueing, Contribution, Interruption, and Co-presence. These conditions are instantiated through everyday manipulation tasks, including paired human-present variants for controlled comparison with standard manipulation. HARP-Bench also provides a demonstration-generation pipeline for dynamic human-present settings. We evaluate VLA models, imitation-learning methods, and heuristic policies on HARP-Bench. Human-present variations challenge current policies, and higher task success does not consistently improve safety. Quantitative failure analysis identifies manipulation and recovery as the dominant remaining challenges. Training with HARP-Bench demonstrations improves human-present performance in simulation. A real-world study on one task family shows improved performance under human contribution, but not interruption, providing initial evidence of the data's utility and identifying limits of transfer. Code is available at https://github.com/UMass-Embodied-AGI/harp.
Read the full abstract
Computer Vision
What You Show Is Not What You Get: Rethinking Demonstration Following in Visual In-Context Segmentation
Visual in-context segmentation uses visual demonstrations to guide predictions for a new image. In SegGPT, we identify background color mapping deviation, where non-target regions sharing a background label receive different output colors, and part-to-parent expansion, where predictions extend beyond the requested part into its parent object. These deviations can occur even when the relevant regions remain distinguishable in internal features. Controlled changes to demonstration colors and requested targets support an account in which demonstrations guide role and color assignments over familiar semantic regions, influenced by learned semantic and color preferences. Building on these findings, we introduce Semantic Contrast Prompt Selection (SCPS). Its semantic contrast encoding assigns separate colors to the requested part and the rest of its object while keeping the remaining scene black. SCPS combines existing retrieval scores with quality estimates from labeled development images to select demonstrations and their binary or semantic contrast encodings. Averaged across seven retrieval methods on three benchmarks, SCPS improves target IoU by 0.054 and reduces leakage into the rest of the object by 22.7% relative to the original binary selectors. Our findings offer a new perspective on understanding and improving demonstration following in visual in-context segmentation.
Read the full abstract
Medical Physics
Phase-Constrained Self-Supervised Reconstruction and Denoising for Ultra-High-Resolution MRI
Ultra-high-field gradient-echo (GRE) MRI reveals fine anatomy with strong susceptibility contrast, but small voxels reduce signal-to-noise ratio (SNR), while susceptibility-induced phase variation and wrapping complicate reconstruction. These challenges are especially consequential for quantitative susceptibility mapping (QSM), which requires denoising GRE phase without blurring anatomy or distorting phase. We propose a measurement-domain self-supervised learning (SSL) framework for joint reconstruction and denoising of complex-valued images from a single noisy acquisition. By splitting acquired k-space samples into input and held-out subsets, the method trains without clean or fully sampled references. An explicit phase-modulation operator, estimated from low-resolution phase and embedded in the unrolled network's encoding model, simplifies phase patterns encountered by the learned regularizer while preserving consistency with acquired complex k-space measurements. We evaluated ex vivo mouse brain MRI at 15, 18, and 72 um isotropic resolution; in vivo mouse brain MRI at 30 um isotropic resolution; and in vivo human brain MRI at 0.3x0.3x0.4mm3 resolution. Across controlled noise levels, SSL improved image-quality metrics in most conditions, preserved fine anatomy, and reduced error propagation into T2* maps and QSM. Ablation studies showed that phase regularization suppressed localized artifacts from rapid phase variation, while in vivo experiments demonstrated denoising with structural preservation. These findings support phase-constrained, measurement-domain SSL for high-resolution anatomical and quantitative MRI when clean references are unavailable.
Read the full abstract
Differential Geometry
The Escobar Constant for Two-dimensional Disks
Let $(M,g)$ be a smooth compact Riemannian surface homeomorphic to a closed disk, with boundary length $L$. We establish sharp upper bounds for its Escobar constant under upper bounds on the Gaussian curvature. If $K_g\leq 0$, then $I(M,g)\leq 2/\pi$, with equality if and only if $(M,g)$ is isometric to a Euclidean disk. If $K_g\leq\kappa$ for some $\kappa>0$, $L<2\pi/\sqrt{\kappa}$, and $\operatorname{Area}_g(M)<2\pi/\kappa$, then $I(M,g)\leq\frac{4}{\sqrt{\kappa}L}\arcsin(\frac{\sqrt{\kappa}L}{2\pi})$, with equality if and only if $(M,g)$ is isometric to the geodesic disk of the same perimeter contained in an open hemisphere of the sphere of constant curvature $\kappa$. We also discuss the higher order Escobar constant for planar domains. In particular, we construct counterexamples to Hassannezhad and Siffert's conjecture.
Read the full abstract
Systems and Control
Scalable Neural Safety Certification via Monotonicity
Learning-based safety certification offers a promising route for verifying complex dynamical systems when explicit models are unavailable, but existing data-driven methods often scale poorly: they treat the system as a black box, rely on dense discretizations or Lipschitz bounds, and consequently suffer from sample complexity that grows exponentially with dimension. This paper shows that a common structural property of dynamical systems–monotonicity–can be used to break this curse of dimensionality. We develop a data-driven framework for robust safety verification and safe controller synthesis for unknown monotone systems using only simulator queries. Our main theoretical result proves that, for monotone systems with upper-closed unsafe sets, safety is completely characterized by the existence of monotone inductive barrier certificates. This structure reduces certificate verification over continuous state spaces to localized boundary checks over finitely many cells. To learn such certificates, we introduce Max-Monotone Networks, a monotone neural architecture with universal approximation guarantees for monotone functions. We then propose a training and refinement algorithm that, upon successful termination, returns formally valid neural barrier certificates and, under mild partition assumptions, requires only $O(n)$ simulator queries. Across high-dimensional benchmarks, including oscillator networks with up to $13{,}659$ states and traffic networks with $1{,}000$ states, our method certifies safety in regimes where prior approaches either do not converge or exceed memory limits. These results demonstrate that exploiting order structure can make neural safety certification both scalable and formally sound.
Read the full abstract
Machine Learning
When gene summaries reveal the answers: Gene Ontology circularity in gene embedding benchmarks
A gene summary can contain the very annotations used to evaluate an embedding of its text. The Alliance of Genome Resources converts Gene Ontology (GO) annotations into sentences, which NCBI Gene displays and GenePT includes in its input. These summaries covered 6,172 of 19,256 human protein-coding genes (32.1%), including 58% of genes with one to ten linked publications. We embedded the same corpus with and without the generated summaries and refitted a function-prediction probe on each version. Among genes with one to ten publications, removal reduced the reported per-gene area under the receiver operating characteristic curve (AUROC) by 0.078 with a linear probe (95% bootstrap interval 0.072-0.084) and by 0.033 with a multilayer perceptron. These estimates use a historical GO scorer that mishandled ties. The original predictions are unavailable for rescoring. A simple TF-IDF encoder also benefited from the summaries, as did models evaluated only on experimental annotations. Replacing generated summaries with UniProt function descriptions recovered much of the lost performance despite little verbatim overlap. UniProt also curates many of the evaluation labels. In mouse and yeast, we found a similar dependence on the source of the description. We introduce GeneProv to compare encoders on matched text and to examine how representation rankings change across GO recovery, non-GO endpoints and co-essentiality.
Read the full abstract
Programming Languages
Keel: A Verified In-Kernel Proof Checker for Proof Carrying BPF
Recent systems such as the eBPF Certificate Framework (BCF) and Proof-Carrying BPF address the imprecision in the Linux eBPF verifier with proof-carrying code. When the verifier's abstract domains cannot prove a safety condition, an in-kernel proof checker checks an untrusted user-space refutation proof. A single bug in this checker can compromise the security of the entire kernel. While formalizing BCF's in-kernel checker, we discovered 13 bugs such as unsound rewrite rules, silently unchecked proof steps, and memory safety errors. We demonstrate that forged certificates can trick the kernel to accept arbitrary unsafe eBPF programs. To address this problem, we propose Keel, a formally verified in-kernel proof checker for the Linux eBPF verifier. First, we specify the checker as a pure functional program in Lean and prove its soundness against bit-vector semantics. We decouple the steps of the proof certificate checker from the mathematical rewrite rules, which enables us to extend the rewrite rules without the need to change the checker. Second, we implement the checker in EmbC, a deeply embedded C fragment, and prove that our C implementation refines the functional specification without undefined behavior or memory leaks. Third, using an amortized potential argument, we prove linear time and memory bounds for the C checker. Keel is correct-by-construction while also being faster than the BCF checker inside the kernel, 1.3X in total and 2.0X on the slowest 1.4% of certificates.
Read the full abstract
Computer Vision
Query-Only Prompt-Agnostic Attacks on Visual In-Context Learning
Visual In-Context Learning (VICL) enables promptable segmentation by conditioning RGB predictions on visual demonstrations, making it attractive for auto-labeling, but its robustness under query-only access and unknown deployment prompts remains underexplored. We study query-only, prompt-agnostic targeted attacks where the attacker observes only returned RGB outputs, without access to model internals or deployment prompts. Treating prompt-conditioned RGB rendering as a distinct attack surface, we introduce two appearance-space attacks: Color Hijack (CH) drives foreground colors toward the background to suppress visibility, while Task Hijack (TH) collapses instance-distinguishing colors toward a shared color assignment. To transfer across unseen prompts, we propose a Self-Prompt Surrogate (SPS) constructed from the clean query and its output. In a paired, matched-budget SegGPT comparison, SPS outperforms the Random-Prompt Surrogate (RPS), reducing CH instance foreground retention from 0.918 to 0.155 and TH palette-aware tolerance distance from 0.345 to 0.225. Across four VICL models on COCO and HierText, CH suppresses foregrounds across semantic-, instance-, and text-style outputs, while TH collapses instance colors under held-out deployment prompts. After palette-based decoding, TH also reduces the decoded instance count and mask retention while increasing instance merges. Finally, at 30% corruption, CH-corrupted annotations from a publicly accessible VICL-based auto-labeling pipeline reduce downstream YOLO-seg mAP50 from 0.761 to 0.281.
Read the full abstract
Computer Vision
MySign: A High-Fidelity Motion-Capture Dataset for 3D Sign Generation in Bahasa Isyarat Malaysia
Progress in 3D sign generation is constrained by the scarcity of high-fidelity 3D sign language datasets, a limitation that is particularly severe for under-resourced languages. We introduce MySign, the first motion-capture dataset for isolated signs in Bahasa Isyarat Malaysia (BIM). Its 5,000 samples cover 1,000 lexical items (glosses) and were produced by five Deaf native signers. Prior datasets that rely on SMPL-X parameters regressed from video provide pseudo-labels, which are often affected by depth ambiguity, inaccurate finger poses, and temporal jitter. MySign instead provides ground-truth SMPL-X sequences retargeted from recordings made with a motion-capture setup tailored for sign language; these sequences offer higher-fidelity motion, particularly in fine-grained hand and finger articulation. A controlled comparison on the same glosses and signers indicates that training on these sequences improves generation over training on such pseudo-labels. We establish MySign as a challenging benchmark for gloss-conditioned 3D sign generation: state-of-the-art models produce visually plausible outputs but fall short of the ground truth, most notably in fine-grained articulation, revealing persistent gaps in modeling articulated sign motion. In contrast, recognition baselines consistently achieve high lexical accuracy, indicating that the dataset reliably supports supervised learning. The dataset is available at https://huggingface.co/datasets/mysigner/MySign
Read the full abstract
Machine Learning
Compositional Conformal Risk Control for Multi-Stage LLM Cascades
Multi-stage large language model (LLM) cascades balance accuracy and inference cost, but reliable deployment also requires controlling error risk and identifying its sources across stages. We propose Compositional Conformal Risk Control (CompCRC), a risk-control framework for pre-specified multi-stage LLM cascades. We decompose the risk of accepting incorrect answers into additive stage-wise contributions over the full query population, linking local risk budgets to a system-level guarantee. CompCRC constructs and freezes candidate budget allocations and acceptance thresholds, selects one candidate on independent data, and certifies its stage-wise risk contributions on separate held-out data. Under conditional exchangeability, we establish a finite-sample guarantee: the marginal expected accepted-error risk of the complete deployment procedure does not exceed the global risk budget. At the reported comparison budget of $\alpha=0.45$, all three stages of CompCRC pass their local checks on MMLU, GSM8K, and HellaSwag. Compared with Global-CRC, which passes system-level risk certification at the same budget, CompCRC reduces observed accepted-error risk by 1.33–2.00 percentage points, improves final accuracy by 0.67–2.00 percentage points, and reduces weighted inference cost by 30.37% on HellaSwag. The selected cost-based budget allocation also improves accuracy per unit cost by 10.6%–46.7% over uniform allocation. Further experiments show that stage-wise statistics identify stages that fail local certification checks, providing diagnostic information alongside system-level risk control.
Read the full abstract
Information Retrieval
PCG-RAG: Progressive Compositional Grounding for Retrieval-Augmented Generation in Complex Web Question Answering
Complex Web question answering requires retrieval-augmented generation (RAG) systems to identify target entities from multi-clue descriptions and connect evidence scattered across long Web pages. Individual pages often support only some of the required semantic constraints, while clues discovered on one page guide subsequent searches on others. However, premature reliance on partially supported entity hypotheses can divert retrieval from the original information need. RAG systems must therefore use partial evidence to guide further searches while seeking the evidence needed to establish the intended entities. We propose PCG-RAG, a novel RAG framework based on Progressive Compositional Grounding (PCG). Progressive Evidence Acquisition directs subsequent searches toward missing evidence for candidate attributes and relations. Compositional Reasoning separates candidate-guided retrieval from evidence-based answering along a directed acyclic graph (DAG) of subquestions. Provisional names make dependent searches specific, while answering tasks use accepted results and unresolved identifying conditions, assessed against the original question. New passages connect the identifying clues to the requested relations, supporting evidence-based downstream answers. Evidence Grounding combines identifying and relational source passages with supported intermediate answers, connecting evidence across Web pages to the original conditions during final generation. On BrowseComp-Plus and WebWalkerQA, PCG-RAG improves accuracy over the leading compared baselines by 5.43 and 5.15 percentage points, respectively.
Read the full abstract
General Economics
The Effect of the U.S. Federal Production Tax Credit on Negative Energy Prices
Negative prices frequently arise in electricity markets and production subsidies are commonly cited as a leading cause. Using data from the U.S. Eastern Interconnection wholesale electricity markets for the period 2000-2023, we document that at least 18 percent of the total hours with negative energy prices cannot solely be attributed to the federal production tax credit (PTC), a large, persistent production subsidy during the period of study. Next, we provide the first causal evidence that the PTC leads to negative energy prices. On average, increasing PTC-eligible wind generation by 1 percent increases the probability of a negative energy price by 3.4 percentage points. However, significant heterogeneity exists across electricity markets, and some markets show an effect that is an order of magnitude larger. Furthermore, the PTC explains only 10 percent of the observed negative prices that could potentially be attributable to it. Finally, we use the causal estimate to calculate a plausible value for the environmental benefits accrued from the PTC subsidy when energy prices are negative.
Read the full abstract
Computation and Language
Beyond Hard Labels: LLM Probabilities Improve Human-Assisted Regression
Large language models (LLMs) are increasingly used for text annotation, but their outputs are often reduced to a single categorical label before downstream analysis. This hardening step discards the model's relative support across categories, which may contain useful information when category boundaries are ambiguous. We study whether retaining the full probability vector improves downstream regression when LLM annotations are combined with a limited amount of human annotation. Using matched soft and hard representations from three LLMs across three social-science text datasets, we compare direct regression and human-assisted correction. Soft inputs are not uniformly better when used directly as outcomes, but after human correction, using the probability vector consistently improves regression efficiency across models and datasets. Analyses of repeated human judgments and controlled simulations further show that these gains arise when probability variation beyond the hard category carries useful information about the human-coded outcome. Our results identify output representation as an important design choice in LLM-assisted measurement and support preserving probability outputs for downstream statistical analysis. Code and reproducibility materials are available at https://anonymous.4open.science/r/soft-label-LLM-D201/
Read the full abstract
Statistical Computation
Statopia: A Prover–Library Ecosystem for Automated Formalization and Proof Discovery in Statistics
Theoretical results in statistics and machine learning rest on long, technically delicate proofs, and fluent arguments generated by large language models are not necessarily correct. Automated formalization makes such arguments mechanically checkable, and automated proving goes further by discovering machine-checked proofs for statements whose proofs are incomplete or missing altogether. Both require reconstructing assumptions from source materials, accessing specialized mathematical infrastructure and managing long proof developments. We present Statopia, an ecosystem that jointly develops Statopia Prover, an independent agent specialized for formalizing and proving results in statistics and machine learning, and Statlib, a Lean~4 library built with the prover and organized for automated use. The prover controls its own execution without relying on external coding agents. It is built for formal proof discovery and checking existing proofs. A natural-language proof, when available, guides its search but is not required: from a statement alone, the prover develops the argument itself and constructs a Lean proof. Its workflow integrates source preparation, statement review, library supported planning and proof construction. Dynamic proof dependency graphs and task groups support parallel, resumable proof development. Statlib's shared definitions and theorem interfaces are organized for retrieval and composition by agents, and its coverage of statistics keeps expanding. Verified results and usage feedback from the prover inform reviewed library updates, so that proof development drives this expansion. A cross-platform application provides an interactive workspace for uploading source files and running tasks locally or in the cloud.