Computer Vision
BiCC: Bidirectional Connected-Component Loss for Instance-Aware Segmentation
Luc Bouteille, Frederic Jonske, Jens Kleesiek et al. (+1 more)
Common
segmentation losses aggregate errors voxel-wise, so lesions influence the objective in proportion to their volume, giving small but clinically critical lesions disproportionately little weight. Instance-aware losses aim to address this mismatch by assigning each lesion its own term. However, blob loss and CC-DiceCE derive their regions solely from annotations, so false-positive components receive no instance-level term. This matters in computer-assisted review, where each false-positive component may require separate inspection, making precision and false-positive burden important alongside recall. We introduce the bidirectional connected-component loss (BiCC), which pairs annotation- and prediction-derived partitions to score predicted components on their own scale. By deriving instances from the predictions, this branch directly penalizes false-positive components regardless of their size. The balance parameter $\alpha$ allows control over the lesion-wise precision-recall trade-off. Across five
datasets with five-fold cross-validation using nnU-Net, BiCC outperforms CC-DiceCE in lesion-wise F1 on four
datasets and blob loss on all five. It significantly improves over DiceCE on three
datasets and matches it on two; CC-DiceCE instead loses up to 0.363 precision by favoring recall. Code is available at https://github.com/TIO-IKIM/BiCC-Loss.
Read the full abstract ▾
All authors Luc Bouteille, Frederic Jonske, Jens Kleesiek, Alexander Jaus
Computer Vision
TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations
Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta et al. (+5 more)
Existing point tracking models face a fundamental tradeoff: they can either track a sparse set of query points over long horizons, or track all points across only short clips. We introduce TrackEverything, a 3D point tracker that breaks this trade-off by representing
videos as persistent 3D scene tracks in world coordinates. Grounded in the insight that
videos are 2D projections of an underlying 3D world, TrackEverything decouples model complexity from
video duration, allowing it to scale with unique physical scene geometry instead. Our approach introduces three key innovations. First, we employ a voxelization-based de-duplication mechanism at sliding-window boundaries to merge co-located tracks, preventing repeated observations of the same surface from redundantly accumulating. Second, we decompose tracking into an endpoint refiner that predicts each point's destination and static-versus-dynamic classification, followed by a lightweight trajectory refiner that decodes dense trajectories exclusively for dynamic points. Third, we propose 3D WAFT, replacing
memory-prohibitive 4D correlation volumes with efficient feature sampling in the scene cloud. To the best of our knowledge, TrackEverything is the first 3D tracker capable of tracking all visible points across
videos exceeding 1000 frames within 40 GB of GPU
memory. On TAPVid-3D, TrackEverything outperforms all open-source all-frame dense 3D trackers by more than 20% APD on short clips, while remaining competitive with state-of-the-art sparse trackers on long sequences, despite tracking far more points.
Read the full abstract ▾
All authors Ayush Jain, Sreeharsha Paruchuri, Ishita Gupta, Fan Zhang, Tanner Schmidt, Jakob Engel, Katerina Fragkiadaki, Adam W. Harley
Computer Vision
WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
Yubo Zhu, Yawen Shao, Ziyun Dai et al. (+27 more)
Video generation begins in text space by authoring a cinematic screenplay, then materializes into pixels. As contemporary
video generators scale to 30 seconds and faithfully follow complex conditions, the textual
prompt largely directs the production, planning how actions, camera trajectories, lighting, and sound unfold across multi-shot sequences. In this paper, we present WanPE, a 397B-parameter
prompt enhancement model trained on 1.05M real-world
videos to master director-level cinematic planning. WanPE formulates shot-level cinematic plans via
video-grounded reverse construction and employs Semantic-Consistency GRPO (SC-GRPO) to faithfully preserve user requirements across shots and over time. To
benchmark this capability, we curate WanPEval, a human-annotated testbed covering durations from 5 to 30 seconds across varying intent granularities, supported by approximately 11K blind pairwise assessments. When powering Wan3.0's
video generator, WanPE-397B boosts human preference over raw user
prompts by 10.66-18.84 points at 5-15 seconds and by a dramatic 50.86 points in the 30-second arena. Ablation studies show that reverse construction demonstrates clear superiority over forward rewriting, while SC-GRPO robustly preserves semantic fidelity across model scales. Ultimately, WanPE leads all evaluated commercial offerings at 5-15 seconds and remains competitive with Seedance 2.5 at 30 seconds.
Read the full abstract ▾
All authors Yubo Zhu, Yawen Shao, Ziyun Dai, Zixun Fang, Kai Zhu, Siyang Sun, Haolan Xue, Chuxin Wang, Tingyu Weng, Jingming Luo, Chen Shi, Lianghua Huang, Yufeng Ai, Yuzheng Wang, Wenyuan Zhang, Yu Shang, Yuxiang Bao, Zoubin Bi, Jie Xiao, Jinbo Xing, Jiaxing Zhao, Chongyang Zhong, Hengjian Chen, Chenwei Xie, Akide Liu, Zhehan Kan, Yu Liu, Wei Zhai, Sheng Zhong, Wei Tong
Software Engineering
Requirement-Bound Verified Commissioning: A Frozen Four-Billion-Parameter Local Model as a Candidate Generator under an External Acceptance Layer with Verification and Release Authority
Mehmet Iscan
An acceptance protocol is developed for sensor-coordinate and polarity binding in mechatronic commissioning. Candidate generation is separated from release authority. Requirements unsupported by a deterministic parser are routed to a frozen local
language model with four billion parameters. Plans are released only when both facts can be derived by an external gate under a sealed grammar. One canonical answer is requested from a gold-standard user when eligible. The protocol was evaluated once under a criterion fixed before
benchmark construction, on 144 tasks written by isolated
agent contexts without access to the gate, grammar, or experimental plan. Three contributions are established. First, candidate generation and release decisions were measured separately. Fabricated ready plans were committed on 21 of 22 routed unanswerable tasks, and all were rejected. The same 83 releases were reproduced without model calls. Second, no false release was observed among 83 releases. A one-sided 95% Clopper-Pearson upper bound of 0.0354 was obtained as a diagnostic under an independent-and-identically-distributed assumption, below the sealed 5% threshold. However, one false release was subsequently recorded among 146 releases outside the
benchmark at seed 0. Third, protection against incorrect user answers was characterized. Both facts were bound from the original text on 13 of 96 answerable tasks. Incorrect answers were released in 169 of 431 pairings on the remaining tasks, including failures involving coordinate exclusion. A deployable questioning policy was not tested because eligibility was determined from the answer key. Gate sensitivity and real user behavior were not measured.
Read the full abstract ▾
Machine Learning
Minimally Invasive Steering of Language Models
Taha Entesari, Jingyu Zhang, Daniel Khashabi et al. (+1 more)
Pre-logit steering adapts a frozen
language model to a test-time reward by adding vectors to its final hidden states. Unregularized reward optimization can substantially alter the output distribution and degrade generation quality. We propose Minimally Invasive Steering Vector Optimization (MISVO), which penalizes interventions using the local KL geometry of the induced
token distribution. The resulting Fisher quadratic measures distributional sensitivity and admits an analytic gradient computed through
matrix–vector products with the frozen
language-model head. We derive an exact decomposition of the sequence-level KL gradient into an analytic Fisher term and a suffix score-function term. For a fixed generation horizon, we show that the suffix term is second order in the steering magnitude and that three Fisher surrogates agree with the full KL gradient to first order. MISVO uses the frozen-reference surrogate to optimize position-specific interventions without updating model parameters. Across preference and code-generation tasks on models with approximately 1B–14B parameters, MISVO achieves the highest mean reward in six of seven model–task settings, with diversity and coherence scores close to those of Best-of-N.
Read the full abstract ▾
All authors Taha Entesari, Jingyu Zhang, Daniel Khashabi, Mahyar Fazlyab
Cryptography and Security
Instrumental Monitor Evasion Emerges Under Ordinary Task Pressure
David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner et al. (+3 more)
A central concern in AI safety is that
agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propensity of LLM
agents to circumvent runtime monitoring as a means of completing ordinary tasks. We introduce EvasionBench, a
benchmark of 50 diverse task-policy pairs in which completing the task requires an operation prohibited by a runtime monitor.
Agents know that their tool calls are monitored and are prompted to continue working when they pause. Across our evaluations, best-of-3 evasion attempt rates reach up to 98% and success rates up to 88%, with substantial variance across models. Claude Fable 5.1 succeeds less often, but frequently makes creative attempts to circumvent the monitor. Evasion generally increases with test-time compute, with higher evasion rates at greater
reasoning effort and
token use. Traces show that
agents encode prohibited commands, decompose operations across tool calls, and retry until relevant context leaves the monitor's history. We also find that GPT-6 Astra's low evasion rate comes with overrefusal, as it frequently abandons otherwise solvable tasks under a denial-of-service
prompt injection. Our findings show that ordinary task pressure can lead to adaptive attempts to evade runtime monitors without an explicit
adversarial objective. Effective oversight must therefore remain robust against repeated attempts, as the persistence that helps
agents solve difficult tasks can also drive them to circumvent their guardrails.
Read the full abstract ▾
All authors David Schmotz, Derck Prinzhorn, Luca Beurer-Kellner, Anselm Paulus, Ameya Prabhu, Maksym Andriushchenko
Software Engineering
Jev in the Wild: A Data-Driven Analysis of the Jev Model's Functionality, Applications and Ecosystem
Guoming Ling, Muen Xue and Zijian Ye
Jev is a fast, low-cost decision model that answers natural-
language questions with choices, binary judgments, and scores. As its public ecosystem grows rapidly, it remains unclear how Jev is used across applications and how public
attention relates to project distribution. To answer these questions, we conduct a large-scale, data-driven analysis of 2,170 publicly available Jev projects collected from GitHub as of September 22, 2026. We find rapid early growth in Jev's public ecosystem, with both new projects and integration into existing repositories. Across diverse domains, projects use Jev for multiple decision purposes and combine its interfaces. Attribute judgment and scoring are widely used, while the use of action selection, content filtering, and model and tool selection varies across domains. These patterns suggest that Jev serves as a reusable decision component whose functionality varies with the surrounding workflow. Meanwhile, public
attention is concentrated in routing and interface
agents and does not track project counts. Our findings provide a quantitative view of Jev's emerging ecosystem and inform the design and evaluation of general-purpose decision models across diverse application contexts.
Read the full abstract ▾
Data Structures and Algorithms
A Nearly Quadratic Lower Bound for Linear Optimization over Convex Bodies in the Membership Oracle Model
Santosh S. Vempala
We prove nearly quadratic lower bounds for randomized
algorithms for linear optimization and uniform sampling over convex bodies in the membership oracle model. For linear optimization, this matches the known nearly quadratic upper bound up to a polylog factor in the dimension. For uniform sampling, this improves on the previous linear lower bound. Our construction also implies the same lower bound for volume estimation.
Read the full abstract ▾
Robotics
Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage
Yuncong Yang, Jinlong Li, Yulong Xue et al. (+4 more)
We present
Underwater C$^{3}$-JEPA (cross-view, control-conditioned, context-extended), an object-centric multi-view predictive world model for near-field heavy-load
underwater ROV salvage. Without contact sensors, it predicts in latent space how the task-object state evolves through contact interaction and under the hydrodynamic lag of the vehicle, from synchronized multi-view RGB observations and vehicle control signals. C$^{3}$-JEPA encodes multi-camera observations into task-object and context
tokens, fuses cross-camera evidence through held-out-view
attention, and directly predicts future states conditioned on control. Weak binding anchors the target and gripper at low annotation cost, while SIGReg sharpens the
geometric representation. Experiments show that the learned representation transfers substantially more task-relevant information to downstream probes than a reconstruction-free latent baseline, while keeping the predictor lightweight. The resulting predictive interface supports model-predictive-control (MPC) candidate evaluation and imagined-rollout behavior-
agent training. Validation on real
underwater video shows the same architecture recovering a withheld camera's object state and staying ahead of persistence, so the recipe transfers beyond simulation.
Read the full abstract ▾
All authors Yuncong Yang, Jinlong Li, Yulong Xue, Feng Wu, Chunwen Zhang, Lei Qiao, Xuyang Wang
Robotics
ReVAMP: Vector-Accelerated Motion Planning for Kinematically-Constrained Systems via Reparameterization
Shrutheesh R. Iyer, Thomas Cohn and Zachary Kingston
Robots often must satisfy one or more constraints during motion planning for real-world tasks. When such constraints reduce the valid configuration space to a measure-zero subset, sampling based planning
algorithms require modifications to draw feasible samples. For many common end-effector constraints, parameterizations built on inverse kinematics (IK) provide an alternate formulation where the constraints are satisfied by construction, allowing directly sampling the feasible set. Despite their elegant approach, parameterized planners have remained slower than vector-accelerated implementations of projection-based approaches, leaving their performance ceiling an open question. We explore a new axis of vectorization built upon reparameterizing the planning space through analytic IK. This approach addresses existing inefficiencies in vectorized projection-based planners and exposes new opportunities for parallelism within the planner. We show that the planner can synthesize plans in microseconds to milliseconds for high dimensional systems (up to 20 dimensions), with complex constraints, up to 10x faster than the current state-of-the-art. Furthermore, we demonstrate how such planning speeds open up avenues for restructuring sequential manipulation pipelines.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Anchored Extra-Proximal Methods: Optimal Higher-Order Methods for Monotone Inclusion Problems
Ruichen Jiang and TaeHo Yoon
We study the deterministic oracle complexity of finding approximate solutions to composite monotone inclusion problems, formed by the sum of a smooth single-valued monotone operator and a maximally monotone set-valued operator, under the tangent-residual criterion. We introduce the Anchored Extra-Proximal (AEP) framework, which combines an anchored extrapolation step with an inexact anchored proximal update satisfying a relative-error condition. The framework recovers the composite Fast Extragradient method in the first-order setting and yields natural second- and higher-order extensions by replacing the operator in the implicit update with its Taylor approximation at the extrapolated point. For every $p\geq 2$, assuming that the $(p-1)$th derivative of the single-valued operator is Lipschitz continuous, we combine this construction with a bisection line search to obtain a $p$th-order method that finds a point with tangent residual at most $\varepsilon$ in $\widetilde{O}(\varepsilon^{-2/(3p-1)})$ oracle calls. This improves all prior upper bounds for $p$th-order methods: in particular, it improves the previous best-known $\widetilde{O}(\varepsilon^{-1/p})$ tangent-residual complexity as well as the classical $O(\varepsilon^{-2/(p+1)})$ bound of higher-order hybrid proximal extragradient methods under the weaker duality-gap criterion. We complement this result with a worst-case lower bound of $\Omega(\varepsilon^{-2/(3p-1)})$ for every deterministic
algorithm in the $p$th-order oracle model, without restricting the
algorithm to tensor steps or any other prescribed update structure. Thus, the proposed method attains the optimal dependence on $\varepsilon$, up to logarithmic factors, for all $p\geq2$.
Read the full abstract ▾
Computer Vision
Hong-Han Wang, Yuntao Wang and Hu Ding
Layer-wise visual-text similarity in
Multimodal Large
Language Models (MLLMs) is widely interpreted as evidence that the
language model progressively integrates visual content into a shared representation space. This reading rests on the assumption that scalar
alignment scores reflect content-level cross-modal interaction. To test this assumption, we apply controlled interventions to the visual stream. Across 13 MLLMs from five families spanning 0.5B to 72B parameters, replacing projector-output visual
tokens with Gaussian noise sharply reduces task accuracy, yet four standard scalar measures (CKA, SVCCA, MIR, and the leading principal-angle cosine) fail to consistently separate the corrupted stream from the original. We call this failure the
alignment illusion and trace it to the shared
language-model pathway: anisotropic MLP down-projections pull visual and text
tokens toward common output directions, producing weight-induced
alignment. Because this component is essentially one-dimensional, we introduce the principal-angle gap (PA gap), defined as the difference between the top two principal-angle cosines, which separates weight-induced similarity from multi-directional visual structure. Under graded visual corruption, the PA gap tracks task accuracy more consistently than the scalar scores we consider; under a structured but irrelevant image, it further exposes regimes in which internal geometry and task accuracy come apart. Internal visual-text
alignment in MLLMs is therefore best read as a
geometric diagnostic of the visual stream inside the
language model rather than a direct proxy for content-level cross-modal interaction, and is most informative when calibrated by controlled task evidence.
Read the full abstract ▾
Computational Engineering
Voxel-based block variational quantum linear solver: a hybrid quantum-classical method for static analysis of solids
Feng Wu, Chen Li, Li Zhu et al. (+2 more)
In solid mechanics, finite element discretization of large-scale static problems produces large sparse linear systems whose solution requires substantial computation time and
memory. The variational
quantum linear solver (VQLS) offers a hybrid
quantum-classical route, but its use in
quantum finite element analysis is limited by the decomposition of nonunitary
matrices, barren plateaus, and the measurement cost of expectation values. We propose a voxel-based block variational
quantum linear solver (Voxel-BVQLS) that combines structured
matrix decomposition, the principle of minimum potential energy, and batched
quantum tests. First, we construct an LCU decomposition of the stiffness
matrix from the recursive block-banded structure of voxel-grid finite element
matrices, with the number of
unitary terms bounded independently of the problem size. Second, we optimize the ansatz parameters using a minimum-potential-energy objective in place of a conventional VQLS loss function, thereby mitigating barren plateaus in the studied problems. Third, we introduce a block-Hadamard test whose
circuit directly estimates weighted sums of multiple inner products, reducing the number of
circuit configurations required per iteration. We assessed the proposed method in noiseless classical simulations using three examples. These examples show that the method reduces both the number of
unitary terms in the LCU decomposition and the number of iterations required to converge, while still yielding solutions of finite accuracy. Voxel-BVQLS thus provides a structured hybrid
quantum-classical framework for
quantum finite element analysis on regular grids.
Read the full abstract ▾
All authors Feng Wu, Chen Li, Li Zhu, Yuxiang Yang, Xu Guo
Artificial Intelligence
A Living Benchmark for Information Retrieval from Electronic Health Records
Jordan L. Cahoon, Chloe O. Stanwyck, Sulaiman Somani et al. (+23 more)
Large
language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve and synthesize information from patient records. Their safety and utility depend on rigorous evaluation, yet existing
benchmarks are manually curated, costly to update, and rapidly become obsolete with evolving technological advancements. We present a scalable framework that automatically generates question–answer pairs from longitudinal EHR notes. Nineteen clinicians validate the
benchmark generator, producing the
Benchmark for Retrieving Information in EHRs (BRIE), a continuously maintainable evaluation
dataset. Across nine LLMs and five inference strategies, state-of-the-art systems frequently omit clinically important information, particularly for questions requiring synthesis across multiple documents and encounters. Because the generator itself is validated, BRIE supports evaluations that static
benchmarks cannot, including the generation of multiple answers that reflect variation in clinician
reasoning for robust performance assessment and continuously refreshing
benchmark content to guard against leakage. Our results demonstrate that scalable
benchmark generation enables rigorous, up-to-date evaluation of clinical LLMs as they are deployed in rapidly evolving healthcare settings.
Read the full abstract ▾
All authors Jordan L. Cahoon, Chloe O. Stanwyck, Sulaiman Somani, Philip Chung, Kevin R Keet, Kameron C. Black, Andrea T. Fisher, Sarita Khemani, Jerry Liu, Stephen Ma, Saloni K. Maharaj, Rita M. Pandya, Eduardo Perez-Guerrero, Priyanka Pillai, Lisa Shieh, David J.H. Wu, James Xie, James C. McAvoy, Teresa Nguyen, Jessica Tran, Lucy Yin, Bridget Lin, Alison Callahan, Jason A. Fries, Nigam H. Shah, Emily Alsentzer
Discrete Mathematics · Cross-listed from math.CO
On the Binary Rank of Matrices with Constant Real Rank
Michal Parnas
We study the problem of determining upper bounds on the maximal binary rank, $b_d$, of a $0,1$
matrix with real rank $d$, for small constant $d$. We prove a general upper bound of $b_d \leq \left\lfloor \sqrt{d2^d + 2d}\right\rfloor -1$. We also develop a general dimension reduction technique of bounding $b_d$ using known upper bounds on $b_{d-1}$ and $b_{d-2}$, as well as prove interesting general structural results on extremal
matrices with binary rank $b_d$. This allows us to get improved non-trivial upper bounds on $b_d$ for constant values of $d$, which imply tight bounds on $b_d$ for $3 \leq d \leq 5$. Our results also imply bounds on the equivalent problem of finding the minimum number of bicliques needed to partition the edges of a bipartite graph whose reduced adjacency
matrix has real rank at most $d$.
Read the full abstract ▾
Artificial Intelligence
ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds
Ming Zhang, Zhenghao Xiang, Peizhong Gao et al. (+17 more)
Scientific discovery begins where known problems end. There, AI systems must engage in exploration: framing hypotheses, designing experiments, and iterating on the results. However, evaluating this ability is difficult: (1) how to verify whether a genuinely new hypothesis holds, and (2) how to determine whether a system has discovered it through exploration or merely recalled related knowledge from pre-training data. To this end, we introduce ExplorationBench, which turns the wicked problem of evaluating scientific exploration into a concrete and tractable framework built on verifiable Alien Worlds: their rules are executable, so every answer can be checked exactly, and they conflict with familiar knowledge, so recall alone cannot solve the tasks. The
benchmark contains two sandboxes, AlienCode (31 discovery targets, 70 tasks) and AlienLogic (24 discovery targets, 70 tasks). Each sandbox provides a flawed manual, task-specific environmental feedback, and a dedicated tool-call schema. Systems use these resources to explore the sandbox, then solve held-out tasks. We evaluate 10 AI systems and find that the strongest systems can acquire and apply unfamiliar rules, while performance varies substantially across trajectories and continued exploration can stall or reverse earlier gains. ExplorationBench represents a step towards AI systems that can acquire and apply genuinely new knowledge through exploration in unknown environments.
Read the full abstract ▾
All authors Ming Zhang, Zhenghao Xiang, Peizhong Gao, Yujiong Shen, Yuhui Wang, Zhonghan Yue, Shihan Dou, Zhangyue Yin, Junjie Ye, Shichun Liu, Weihuang Zheng, Jiahao Chen, Jiayi Chen, Hongzhang Liu, Jiaqi Shao, Tao Gui, Qi Zhang, Xuanjing Huang, Suncong Zheng, Maxm Pan
Machine Learning
Beyond Compression: Training Latent Representations for Stable Long-Horizon Rollout in Neural Surrogate Solvers
Andreas E. Robertson, Ashley T. Lenau, John D. Shimanek et al. (+5 more)
Latent neural surrogate solvers, or latent dynamics models, accelerate simulations of time-dependent physical systems by evolving a compressed latent space rather than resolving full-resolution fields directly. In principle this reduces computational cost and simplifies learning, but in practice errors often accumulate rapidly during long autoregressive rollouts, limiting predictive utility. We show that this instability does not stem from the latent representation itself, but arises when it is trained solely for reconstruction, producing representations poorly suited to long-horizon
forecasting. We systematically evaluate training-level interventions that align latent representations with long-horizon rollout: Koopman operator learning and Hamming noise injection during autoencoder training to improve compression, together with noise injection and multi-step rollout fine-tuning to improve dynamics. Interventions that improve long-horizon rollout stability often degrade conventional training metrics, including reconstruction and one-step prediction accuracy. Collectively, these interventions reduce long-rollout error by approximately 40% and match or exceed the accuracy of full-resolution models on two physics
benchmarks, while requiring 2 orders of magnitude fewer floating point operations and half the GPU
memory. Applied to mesoscale
crystal-plasticity simulations of high-cycle fatigue, the resulting surrogate achieves stable extrapolation over horizons orders of magnitude beyond those observed during training. More broadly, these results show that neural compression should be designed not merely to reduce dimensionality, but to restructure the solution space for stable dynamical
evolution, a key requirement for reliable, efficient neural surrogates in scientific applications.
Read the full abstract ▾
All authors Andreas E. Robertson, Ashley T. Lenau, John D. Shimanek, Benjamin A. Jasperson, Vivek Oommen, David L. Damm, Krishna Garikipati, Remi Dingreville
Data Structures and Algorithms
Practical and Space-Efficient LZ77 and LZ Pre-Compression via String Synchronizing Sets
Jonas Ellert and Lukas Nalbach
The Lempel-Ziv (LZ77) factorization decomposes a text into the least possible number $z$ of phrases that each refer to an earlier occurrence. It is this phrase count, rather than the encoded size, that governs the size of LZ-based compressed indexes, and computing a factorization with few phrases is a time and space bottleneck in their construction. In practice, computing LZ77 quickly typically requires the suffix array. In theory, the exact LZ77 factorization, and a 3-approximation of it, can be computed more space-efficiently without the full suffix array [SPIRE 2023]. These
algorithms have remained unimplemented, because two of their components resist a direct implementation: a lookup table that degenerates to patterns of length at most two for realistic inputs, and an orthogonal range reporting data structure that is impractical. We replace both, fine-tune every remaining stage, and obtain the first practical implementation, which runs in space close to the text rather than to the suffix array. On one thread, our 3-approximation factorizes 12-19x faster than the classical LPF
algorithm while using 14x less
memory; on 32 threads, even our exact
algorithm is 1.4-2.9x faster than parallel LPF, at 9x less
memory. In practice the approximation ratio stays far below 3. As a side result, passing only the perfect phrases of our 3-approximation to a downstream compressor yields a precompressor that is on par with the state of the art [Dinklage, SEA 2026] in compression ratio, and better in
memory consumption and parallel throughput.
Read the full abstract ▾
Artificial Intelligence
SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
Xinyue Zeng, Jiawei Zhang, Yujun Yan et al. (+1 more)
Long-horizon
reasoning remains a central challenge for large
language models (LLMs) under sparse-reward regimes. We argue that this brittleness arises from two biases induced by complex
reasoning spaces: an exploration bias, where models are drawn toward locally plausible but structurally unstable branches, and a compounding bias, where small local deviations accumulate across depth and suppress rare rewards. We introduce Symbolic Closure Analysis (SCA) as a theoretical lens characterizing how branching structures and sparse rewards induce these biases in long-horizon
reasoning with local admissibility, and as a design principle for structural priors in less formal
reasoning tasks. Motivated by this analysis, we propose SAGE (Structural Admissibility-Guided Exploration), a unified framework that injects structural guidance to alleviate exploration bias and compounding bias in long-horizon
reasoning. SAGE combines two complementary structural guidance: algebraic sparsification, which projects locally admissible candidates onto operator-indexed algebraic subspaces to suppress spurious branching and mitigate exploration bias, and
hyperbolic structural guidance, which embeds
reasoning states into a negatively curved space to provide dense depth-wise signals and mitigate compounding bias. Across 12
benchmarks and 7 model families, SAGE outperforms competitive baselines. In particular, SAGE achieves up to an 8-fold improvement on the Andrews-Curtis problem, an open real-world long-horizon task. Code is available at: https://github.com/Susan571/SAGE-NeurIPS2026.
Read the full abstract ▾
All authors Xinyue Zeng, Jiawei Zhang, Yujun Yan, Dawei Zhou
Computer Vision
Ego-Exo4D Human Meshes Dataset: 4D Human Motion Reconstruction for Ego-Exo Captures
Abhiram Maddukuri and Georgios Pavlakos
Ego-Exo4D is a large-scale
dataset providing synchronized
egocentric and multi-view exocentric
video, a rich resource for skill learning and assessment, procedural activity understanding, and
embodied AI. However, the
dataset ships with only sparse 3D human pose annotations, and reconstructing dense human motion from its multi-view captures is nontrivial. To this end, we present Ego-Exo4D-HM, a large-scale
dataset of 4D human motion reconstructions for Ego-Exo4D's captures, and release the accompanying reconstruction pipeline. The code,
dataset, and documentation can be found at https://abhiram824.github.io/egoexo4d_human_meshes.
Read the full abstract ▾
Artificial Intelligence
Jev-Mobile: Jev as an Executor for Mobile GUI Agents
Linghua Zhang
Vision-
language models (VLMs) have become a common foundation for autonomous mobile GUI
agents, but most existing systems rely on the VLM for both planning and action grounding at nearly every interaction step, leading to substantial latency and model-serving cost. We introduce Jev-Mobile, which shifts this paradigm to low-frequency VLM planning and high-frequency lightweight execution: the VLM specifies local goals, the accessibility tree defines a structured executable action space, and Jev, a fast typed decision model, repeatedly selects actions within this space. This design allows multiple GUI actions to be executed under a single VLM decision, reducing expensive VLM inference while preserving adaptive interaction. On the full AndroidWorld task suite, Jev-Mobile achieves 79% task success, compared with 78% for SeeAct-V and 84% for a Step-wise VLM baseline. Among successful trajectories, it reduces mean end-to-end execution time by 32.7% and mean model API cost by 73.4% relative to Step-wise VLM. These results show that decoupling high-level VLM
reasoning from low-level action execution can substantially improve mobile GUI
agent efficiency while maintaining competitive task performance.
Read the full abstract ▾
Machine Learning
Intrinsic-Extrinsic Coupling in Learning Dynamics
Qinyou Wang
A learner's current observations need not determine its response to further training. We formulate intrinsic-extrinsic coupling through the continuation-conditioned value of a constrained learning-state intervention, with observation-relative fibers describing present agreement. An executable finite-frame classifier-head write protects current logits while repairing specified historical margins under finite-precision acceptance checks. We distinguish local admissibility, continuation-conditioned intervention value, and complete-policy performance. A matched four-
cell contrast identifies readout-specific non-additivity between the same intrinsic intervention and alternative external continuations. In a CLINC-derived class-incremental setting, replay changes the write's 32-update contribution from five correct predictions to zero. Nonzero interactions also occur under output
distillation, with a RoBERTa backbone, and under optimizer-native SGDW dynamics. Under SGDW, correct-count interactions are negative in all three activated roots at 128 updates, showing that coupling need not imply positive synergy. The mathematical analysis distinguishes feasible local repairs and favorable terminal outputs from training-reachable repair regions. Separate coordination tests show that content controls match or exceed the development gain, while a five-root fresh-test comparison with Fiber present in every arm shows root-dependent rather than uniformly beneficial correct-count effects. On the secondary cross-
entropy readout, guided allocation yields lower mean loss than standard replay in all five pairs. Together, these results make intrinsic-extrinsic coupling operational by connecting executable state geometry to continuation-conditioned value, matched interaction identification, and closed-loop coordination, while separating identified coupling from complete-policy performance.
Read the full abstract ▾
Computation and Language
ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints
Sriram Kannan, Swetha Saseendran, Vishnu Vardhan Reddy Kandi et al. (+3 more)
U.S. employment-discrimination complaints describe complex event sequences that are not explicitly captured by lexical or
embedding-based representations alone. We present ARGUS, a source-grounded pipeline that combines a 5W1H-inspired schema, legal-domain models, and LLM-based structured generation to construct document-level Event Knowledge Graphs (EKGs) from CourtListener complaints. ARGUS extracts fact-bearing statements, builds chunk-level event graphs with participant, temporal, and causal structure, and merges them into document-level representations. We evaluate graph quality through human and multi-model assessment and test downstream utility on claim classification and legal QA. The graph-structured classifier outperforms raw and linearized baselines on the held-out set, and EKG-only
retrieval improves document-scoped QA, while open-
retrieval gains remain limited by low first-stage candidate recall. These results suggest that EKGs are most useful for organizing and
reasoning over evidence once relevant material has been retrieved.
Read the full abstract ▾
All authors Sriram Kannan, Swetha Saseendran, Vishnu Vardhan Reddy Kandi, Leslie Barrett, Madhavan Seshadri, Enrico Santus
Numerical Analysis · Cross-listed from math.AP
Reconstruction of the Initial Condition for a Non-Homogeneous Heat Equation from Finite Measurements
Randy Dollente, Samuel Frerichs, Hee Seok Nam et al. (+3 more)
We address the inverse problem of reconstructing the initial temperature distribution in a one-dimensional non-homogeneous heat equation with Dirichlet boundary conditions from a finite number of pointwise-in-time measurements at a single spatial location. We propose an explicit approximation scheme that incorporates the source term and utilizes a refined sequence of measurement times. Unlike previous approaches that often rely on exponentially growing observation times, our chosen time sequence allows for efficient recovery within a fixed time horizon. We establish algebraic convergence rates under suitable regularity assumptions on the initial data and the forcing, and we validate the theoretical sharpness with numerical experiments for varying numbers of measurements.
Read the full abstract ▾
All authors Randy Dollente, Samuel Frerichs, Hee Seok Nam, Jianru Shen, Grace Walters, Young Hwan You
Software Engineering
NEUROTESTGEN: Neuro-Symbolic Guided Test Generation with Large Language Models
Ruixin Zhang, Jiho Shin, Hung Viet Pham et al. (+1 more)
Ensuring high structural coverage remains a fundamental challenge in automated test generation, particularly for complex software systems where reaching specific lines or branches requires satisfying intricate control- and data-flow constraints. Large
Language Models (LLMs) have recently demonstrated strong capabilities in producing human-like test cases; however, they often struggle to generate inputs that satisfy precise path conditions. Conversely, symbolic execution can systematically derive such constraints, but it often fails to construct realistic, executable test cases and is constrained by scalability limitations. In this paper, we introduce NEUROTESTGEN, a hybrid approach that integrates symbolic execution with LLM-driven test synthesis to generate test cases targeting on-demand code coverage. Given a set of target statements within a method, NEUROTESTGEN first employs a symbolic analysis engine (i.e., the Z3 SMT solver) to extract path-specific constraints and construct a symbolic guidance specification for the desired coverage goal. This specification is then used to guide an LLM in synthesizing concrete test cases that are both structurally valid and semantically meaningful. For paths involving complex object-related constraints that are difficult for SMT solvers to handle, NEUROTESTGEN leverages LLMs to infer plausible constraints. Furthermore, NEUROTESTGEN incorporates an iterative feedback loop that validates LLM-generated tests and provides corrective guidance until the target line or branch is covered or a limit is reached. Our empirical evaluation on a widely used
benchmark demonstrates that NEUROTESTGEN significantly outperforms the state-of-the-art approach across multiple LLMs, including Llama 3.3 70B1, GPT-4o Mini, Claude 3.5 Haiku3, and Claude Sonnet 4.6.
Read the full abstract ▾
All authors Ruixin Zhang, Jiho Shin, Hung Viet Pham, Song Wang
Artificial Intelligence
Search-Aware Reinforcement Learning for Multi-Component Query Understanding in Roblox Game Search
Nayoung Choi, Shengjian Chen, Xiaokai Wei et al. (+6 more)
Query understanding (QU) in production search systems has typically relied on separate models for each subtask, such as search intent classification, attribute extraction, and query rewriting. Large
language models (LLMs) now make it possible to consolidate these subtasks into a single model that emits a unified QU output. This consolidation, however, introduces a new optimization challenge. A single model serves multiple components, each with a distinct downstream role within the search pipeline, and the utility of each depends on how the underlying search engine acts on it rather than on agreement with static labels. We present a search-aware reinforcement learning (RL) framework for multi-component QU based on a distill-then-RL paradigm. Teacher-student supervised fine-tuning (SFT) first yields a schema-compliant small policy. The RL stage then starts from this policy, executes each QU plan on the live production search engine, and optimizes every component with a reward tailored to its operational role, rather than relying on a single reward tied to the final search outcome. On a large-scale user-generated game platform, this component-specific optimization raises NDCG@20 by 8.9 points over the SFT policy and by 3.5 points over a single end-to-end reward. The resulting small, low-latency student models also surpass their much larger teacher, and our final model is being incrementally deployed in production.
Read the full abstract ▾
All authors Nayoung Choi, Shengjian Chen, Xiaokai Wei, Wenzheng Zhang, Daiyao Yi, Rachit Pareek, Vincent Su, Michelle Gong, Jinho D. Choi
Systems and Control
GridSFM: A Foundation Model for Solving AC Optimal Power Flow
Luke Bhan, Weiwei Yang, Margaret Capetz et al. (+1 more)
We introduce GridSFM, a framework that combines a pretrained foundation model across grid
topologies with physics-informed fine-tuning for solving AC Optimal Power Flow (AC-OPF) at scale. It is a $15$ million parameter physics-inspired graph neural network pretrained across $54$
topologies of $500$ to $4{,}000$ buses. Our model attains a $2.45\%$ zero-shot generation-cost error on a $10{,}000$ bus case held-out operating conditions with no degradation as system size grows. Building on this, we pair the pretrained backbone with a physics-informed fine-tuning design based on Newton's method for power flow. With only $100$ solved instances, GridSFM adapts to unseen grids up to $10{,}000$ buses. We show it out performs single
topology, dedicated neural network models that are trained more data, both in terms of cost and solver iterations when deployed as warm starting points. In designing this foundation model, we overcome the fact that the feasible set for AC-OPF can be disconnected. This is an obstruction that prevents any continuous neural network from approximating the solution map. To do so, we lift the problem and relax its constraints with logarithmically penalized slacks. We prove that the resulting elastic feasible set is contractible, that the AC-OPF minimizers remain minimizers of the elastic problem above an explicit penalty threshold, and that projecting an approximate solution back onto the AC-OPF feasible set is well posed. We release all models, data, and code so that the community can build on a shared starting point for AC-OPF.
Read the full abstract ▾
All authors Luke Bhan, Weiwei Yang, Margaret Capetz, Baosen Zhang
Computational Complexity · Cross-listed from quant-ph
Optimal spectrum estimation
Ainesh Bakshi, Apoorv Vikram Singh and Xinyu Tan
We prove that the spectrum of an unknown $d$-dimensional
quantum state can be estimated to error $\varepsilon$ in total variation distance using \[ O\!\left(d^2\min\left\{ \frac{1}{(\varepsilon\log d)^4},\; \frac{1}{(\varepsilon\log d)^2} \right\}\right) \] copies. This matches the recent lower bound of Wang. When restricted to unentangled measurements, we give an
algorithm with an additional factor of $d$ in copy complexity, which we
conjecture to be optimal. We develop a framework for recovering the small
eigenvalues of a
quantum state by matching Chebyshev moments. We bound the variance of each Chebyshev moment estimate in terms of scalar derivatives of the corresponding
polynomial, using classical and
quantum Efron–Stein decompositions. Different rescalings of the Chebyshev
polynomials balance approximation error and variance, yielding two regimes in our copy complexity bound.
Read the full abstract ▾
Computation and Language
Do Audio Language Models Hear and Read Distinctive Features Alike?
Yuanhao Chen and Peter Chin
Audio
language models pass
speech and text through a single decoder. We ask whether that decoder represents a distinctive feature in the same direction when a phoneme is heard and when it is read. For minimal pairs of phonemes differing in one feature, we take the offset between the two members' mean representations. Averaging those offsets gives a direction for each stream, and we measure the cosine between the two. Because the two streams already agree about arbitrary phoneme pairs, we compare every measure against a reference built from random pairings rather than against zero. We apply this to 6 models, 7 features and 15
languages from 11 families. Only voicing in the two Qwen2.5-Omni models exceeds that reference after correction for multiple testing, and the reference varies by a factor of seven between models. In three of the six models, voicing has one direction in audio across the 14
languages with enough minimal pairs to measure it, and every
language pair agrees in two of them. The model family, not the model size, predicts which stream represents a feature.
Read the full abstract ▾
Distributed Computing
Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
Zeno De Angeli, Philipp Jovanovic, Lefteris Kokoris-Kogias et al. (+2 more)
Dual-mode consensus protocols are fast when the network is partially synchronous and remain live under asynchrony. We introduce Steelhead, a dual-mode mechanism that composes a partially synchronous and an asynchronous commit rule over one DAG: every k-th round is decided by the asynchronous rule, whose leader a common coin reveals after the votes, and all other rounds by the partially synchronous rule. Every interval, validators replay the committed DAG under each candidate period, adopt the one with the fewest expected message delays, and fall back to k = 1 when the output stalls; the asynchronous rule applied to the coin rounds alone keeps the protocol live. Steelhead sends no message beyond the DAG's blocks, not even to agree on the period, and opens a coin only on the rounds that need a hidden leader. It is generic over pairs of DAG commit rules that share a committee; we instantiate it with Mysticeti and Mahi-Mahi at n >= 3f+1 and with the two variants of BlueBottle at n >= 5f+1. We prove it safe and live, and provide mechanized proofs in Lean 4. In simulation, Steelhead matches the partially synchronous protocol in a healthy network, stays close to the asynchronous one when network conditions stall the partially synchronous one, and adapts quickly in both directions.
Read the full abstract ▾
All authors Zeno De Angeli, Philipp Jovanovic, Lefteris Kokoris-Kogias, Markus Legner, Alberto Sonnino