Computational Engineering
Multi-Agent Path Planning via Compatible Encounter-Space Allocation in Crowded Spaces Dynamically Occupied by Work Activities
Boda Liu, Xuezhi Yang, Bin Yang et al. (+1 more)
Lifelong multiagent path planning on construction floors must accommodate continually changing goals and work occupancy. Existing planners can update paths and timing online, but work motion space coupling changes the spatial basis of unfinished encounters, while rerouting affects later encounters. Planning must therefore construct and maintain local encounter possibility. We propose Width based Planning with Compatible Encounter Space Allocation (WP), which constructs shared passage relationships from actual encounter demands and real time widths. Shared channels, ordered anchors, and urgency based updates coordinate successive encounters while retaining individual greedy motion between them. A necessary and sufficient width condition for fixed-point position exchange and a necessary directional condition for composite exchange provide
geometric grounds for channel construction and encounter relocation. In crowded floor computational experiments, WP maintained route continuation after occupancy changes and enabled multi
agent clearing, with infrequent, brief near stops. Complete run comparisons with four methods showed 25.2% to 52.2% more mean goal arrivals than the best baseline at each configuration of 5 to 10
agents, with lower mean computation time than the rolling horizon K_CBS adaptation. The contribution is a planning principle that constructs and continuously maintains local passage relationships from real time space, unifying shared spatial allocation and conditional local clearing to extend lifelong planning to work motion space coupling.
Read the full abstract ▾
All authors Boda Liu, Xuezhi Yang, Bin Yang, Shu Li
Information Theory
Routing Optimality for Demand Graphs of Matching Number at Most Two
Xiaohong Cai and Yulin Chen
We prove that network coding and fractional routing have the same capacity region in undirected networks whose demand graph has matching number at most two, that is, when no three demand edges have pairwise disjoint endpoints. The metric-packing reduction of Liu et al. reduces this problem to a distance-weighted communication inequality on the fixed graph $\Gamma_{3,3}$. We first prove two
entropy inequalities for sessions between designated terminal pairs on $\Gamma_{3,3}$. We then extend this result to sessions with arbitrary endpoints to obtain the distance-weighted communication bound required by the reduction. The proof combines conditional
entropy inequalities with two graph contractions and an information inequality for deterministic interaction. Combining this inequality with the existing reduction establishes routing optimality for this class of demand graphs.
Read the full abstract ▾
Formal Languages and Automata
Jumbled Simon's Equivalence and Embeddings
Pamela Fleischmann, Annika Huch, Sungmin Kim et al. (+2 more)
Jumbled scattered factors are a generalisation of scattered factors (or subsequences) where a jumbled scattered factor is obtained from another word by deleting and rearranging letters. For limiting the number of rearrangements, we distinguish $\ell$-jumbled scattered factors where $\ell$ limits the number of letters that may occur rearranged. For instance, $\mathtt{car}$, $\mathtt{start}$, $\mathtt{rat}, \mathtt{cat}$ are jumbled scattered factors of $\mathtt{abstract}$ even though $\mathtt{car}$, $\mathtt{start}$ and $\mathtt{cat}$ are no scattered factors and each need one jumble. An example for a jumbled scattered factor with $2$ jumbles is $\mathtt{tatar}$. In this work, we investigate two problems on jumbled scattered factors from an algorithmic perspective. First, we give
algorithms for testing jumbled Simon's equivalence where two words are equivalent if they share the same $\ell$-jumbled scattered factors up to length $k$. Second, we investigate how to count the possible occurrences of a jumbled scattered factor – the jumbled binomial coefficient. After defining the jumbled binomial coefficient, we study jumbled
embeddings and factorisations of such as well.
Read the full abstract ▾
All authors Pamela Fleischmann, Annika Huch, Sungmin Kim, Tore Koß, Emil Wiards
Computation and Language
Text-Only vs. Image-Aware VLM Judges for Manga Translation Evaluation
Subaru Kimura and Jun Suzuki
In manga translation, visual context outside
speech-bubble text, including speaker identities, referents, and scene tone, is depicted in page images, making it natural to refer to images during translation evaluation. However, most conventional manga translation evaluations rely solely on text-only automatic metrics, leaving the impact of image input insufficiently explored. We propose a practical validation framework that employs the same
vision-
language model (VLM) as both a text-only judge (TOJ) and an image-aware judge (IAJ) to investigate evaluation divergences associated with image-aware evaluation procedures. We use a Japanese-English manga
dataset of official translations aligned at the page and
speech-bubble levels. First, adding page images to TOJ improved the primary VLM's detection of deliberately injected, visually dependent degradations. Second, we analyzed evaluation divergences between TOJ and IAJ, finding different error counts and error-category distributions. Human verification did not reveal a consistent preference between TOJ and IAJ.
Read the full abstract ▾
Software Engineering
SpecCloak: Probing Harmful Code Generation through Engineering Specifications
Wenbin Chen, Jiexin Wang, Guanting Wu et al. (+2 more)
The code generation capabilities of large
language models (LLMs) can equally be misused to implement harmful functionality, underscoring the need to understand their safety behavior in response to programming requests. While request phrasing is known to influence refusal, it remains unclear whether the form in which coding task requirements are stated affects the refusal process for malicious code generation. We introduce PseudoSpec, a template that organizes functional requirements as engineering specifications, and investigate its effects through controlled comparisons, representation analysis, and activation interventions. Across five open-weight models, removing explicit risk keywords only partially reduces refusal, whereas specification prompting substantially lowers refusal even when these keywords are retained. This reduction accompanies consistent shifts toward code-output-related representations, and interventions along condition-difference directions alter refusal behavior. Output analysis further distinguishes code-related responses from generation degeneration. Building on these findings, we propose SpecCloak, a black-box red-teaming framework combining PseudoSpec with discriminator-guided optimization, achieving an average execution-verified attack success rate of 28.91% across eight target models on RedCode-Gen. We also introduce SpecReveal, a defense prototype combining natural-
language intent reconstruction with dual-view detection without target-model fine-tuning. It achieves a 96.88% attack detection rate in a separate
prompt-detection evaluation, with false positives assessed on benign programming and specification-style inputs. These results connect specification-induced response differences to practical security consequences and identify intent reconstruction as a complementary detection approach.
Read the full abstract ▾
All authors Wenbin Chen, Jiexin Wang, Guanting Wu, Jiaxi Liang, Yi Cai
Graphics
Content-Edited Layout Generation for Graphic Design
Shirong Yang, Zheyi Pan and Ying Cao
In this paper, we formulate a novel form of conditional layout generation for graphic design, termed content-edited layout generation(CELG). CELG extends conventional content-aware layout generation (CLG), which generates a foreground layout for a fixed background image. The key distinction is that CELG treats the input image as an editable visual asset and, conditioned on a textual design intention and a foreground requirement that may be empty, produces an adapted background together with its layout. To study this task, we introduce Search-Compare-Edit(SCE), a data construction framework that supplies the paired supervision missing from existing design
datasets. Starting from professional design canvases and their layouts, SCE synthesizes plausible pre-edit source images and corresponding editing instructions, yielding InstructEdit, a
dataset of aligned source images, target canvases, instructions, and layouts. Based on the generated data, we train a two-flow
multimodal flow matching model that couples a pretrained image editor with a layout flow
transformer, enabling background editing and layout generation simultaneously within a unified framework that more closely reflects real-world design workflows. Our experiments systematically demonstrate the value of CELG as a distinct task and the performance advantages of the proposed model.
Read the full abstract ▾
Machine Learning
Stable-Plastic Subspace Construction for Differentially Private Continual LoRA
Jin Liu, Ning Xi, Yinbin Miao et al. (+3 more)
Continual learning (CL) adapts pretrained models to a sequence of tasks while retaining knowledge acquired from earlier tasks. When task data are sensitive, differential
privacy (DP) provides record-level protection, but maintaining both adaptation and retention under
privacy constraints remains challenging. We study this problem in continual low-rank adaptation (LoRA) and observe that: 1) private training increases forgetting primarily during subsequent adaptation rather than initial task acquisition; 2) jointly perturbing both LoRA factors introduces a non-negligible bilinear noise interaction; and 3) DP aggravates the stability-plasticity dilemma, hindering both knowledge retention and adaptation to new tasks. Based on these observations, we propose DP-SPA, which constructs a stable subspace from previously privatized updates and a plastic subspace from pretrained weights within its orthogonal complement. The method fixes these bases and privately optimizes only the LoRA factor, eliminating the bilinear noise interaction within each step. Before merging each task update, it rescales stable-direction coefficients using historical and current update energies. We establish a
privacy guarantee and show that recalibration does not increase historical overlap and tightens a conditional upper bound on old-task loss increase. Experiments across five
datasets, eight settings, and multiple
privacy budgets show that DP-SPA improves average accuracy and reduces forgetting compared with the evaluated baselines.
Read the full abstract ▾
All authors Jin Liu, Ning Xi, Yinbin Miao, Junkang Liu, Ke Cheng, Jianfeng Ma
Computer Vision
DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous Driving
Shuzheng Wang, Haoxuan Li, Shengzhen Li et al. (+5 more)
Vision-
Language Models (VLMs) and world models have demonstrated strong capabilities in semantic understanding and future scene
evolution for autonomous driving. However, effectively integrating both capabilities for trajectory generation remains challenging. In this work, we propose DriveWLA, a unified World-
Language-Action model based on Mixture-of-
Transformers (MoT) that jointly models semantic understanding, future scene dynamics, and trajectory generation. DriveWLA consists of three experts: a World Expert for future prediction, a
Language Expert for semantic understanding, and an Action Expert for trajectory generation. We further introduce Cross-Expert
Attention, which enables controlled information flow across experts while aligning semantic and dynamic representations. To improve trajectory generation beyond imitation learning, we apply Flow-GRPO reinforcement learning post-training to refine the Action Expert. Extensive experiments show that DriveWLA achieves superior performance in both open-loop and closed-loop evaluation. DriveWLA achieves 92.3 PDMS on NAVSIM v1 and 90.1 EPDMS on NAVSIM v2, demonstrating strong performance among VLM-based and world-model-based planners. Without specific fine-tuning, DriveWLA further demonstrates strong zero-shot generalization to HUGSIM, nuScenes, and Bench2Drive. These results validate the effectiveness of our unified World-
Language-Action modeling, establishing DriveWLA as a generalizable framework for autonomous driving.
Read the full abstract ▾
All authors Shuzheng Wang, Haoxuan Li, Shengzhen Li, Chenxi Wu, Yajing Sun, Lu Hou, Wenyu Liu, Xinggang Wang
Computer Vision
Visual Dependence Does Not Imply Answerability: A Systematic Analysis of Answerability Signals in Frozen InstructBLIP
Minjun Kim, Hyunmin Song and Changwon Lim
Visual question answering models often produce plausible responses even when the available visual evidence is insufficient to support a valid answer. Although prior work has introduced
benchmarks and abstention mechanisms for unanswerable visual questions, it remains unclear which signals derived from a frozen
vision-
language model reliably indicate answerability on unseen image-question pairs. We systematically evaluate answerability signals on a stratified 10K subset of UNK-VQA using frozen InstructBLIP, covering predictive uncertainty, cross-modal
alignment, visual grounding, visual dependence, internal representations, and learned probes. Answerability discrimination remains weak, with test AUROC largely confined to 0.50-0.54. CLIP
alignment yields the highest point estimate but does not significantly outperform generation confidence under paired bootstrap analysis. Targeted removal of question-relevant visual evidence causes substantially larger changes in answer confidence than same-size random masking, yet intervention sensitivity provides essentially no answerability discrimination. Increasing probe capacity, combining multiple signals, and adding reason-aware supervision do not provide robust improvements, while post-freeze cross-validation yields similarly weak discrimination. Selective-answering analysis shows limited usable coverage under low-risk operating criteria. Failure-mode analysis shows that the relative utility of individual signals varies across perturbation mechanisms. Taken together, these results show that, on our UNK-VQA subset with frozen InstructBLIP, visual dependence, uncertainty, semantic
alignment, and static representations are not robust standalone proxies for answerability. Our findings emphasize the need to distinguish a model's reliance on visual evidence from whether that evidence is sufficient to support an answer.
Read the full abstract ▾
Machine Learning
FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention
Guoxia Wang, Qianyue He, Siming Wu et al. (+6 more)
Long-context training of large
language and
multimodal models couples structured
attention masks (document, prefix-LM, share-question, sliding-window, block-sparse) with multi-node context parallelism, making the mask a dominant bottleneck. FlashMask's column-wise sparse mask compresses them from $O(n^2)$ to $O(n)$ via four query-axis boundary vectors, covering broad structured patterns. Implemented for Ampere GPUs, it neither exploits FlashAttention-3's TMA/WGMMA warp-specialized pipeline on Hopper nor supports distribution. The column-wise sparse mask is indexed by key positions but stores query-axis interval boundaries. Under any multi-chunk context-parallel assignment, it reduces per-rank mask localization to a provably zero-communication clip–shift–max on the boundary vectors, compatible with the single-GPU kernel. FlashMask-3 introduces a mask-aware Hopper kernel with three-role warp specialization atop FlashAttention-3's TMA/WGMMA pipeline, plus a mask-aware distributed extension: zero-communication mask localization, a sparsity-aware load balancer (HCC-IPO), and a mask-aware compute-communication overlap with mask-driven communication
pruning, whose forward all-gather uses
topology-aware hierarchical routing. On a single H100 across 12 masks at 4K–128K context, it improves achieved TFLOPs over FlashMask, FlexAttention, and MagiAttention by 45–141%, 34–71%, and 2–44%. At context-parallel degrees 4–32 with 8K sequence per device, it attains 31–75% compute-communication overlap efficiency and improves throughput over Megatron-Core CP ring, Megatron-Core CP all-gather, and MagiAttention by $1.80\times$–$3.71\times$, $1.71\times$–$2.92\times$, and $1.09\times$–$1.46\times$. In end-to-end training of a 118B-A14B MoE at 128K on 128 H100 GPUs, it raises throughput by 7.3–11.0% over a Dual Chunk all-gather baseline, with
attention forward+backward 24.5–44.9% faster.
Read the full abstract ▾
All authors Guoxia Wang, Qianyue He, Siming Wu, Haoyang Xie, Qiwen Bao, Jinle Zeng, Jiabin Yang, Tian Wu, Dianhai Yu
Artificial Intelligence
PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning
Changguo Jia, Zhiyou Xiao, Xinbei Ma et al. (+5 more)
Extended chain-of-thought
reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter
reasoning. We introduce PaceReasoner, a label-free test-time reinforcement learning framework that uses a model's LONG responses to improve its SHORT-mode accuracy. Both modes share a trainable policy, creating a need for reliable supervision, sufficient SHORT training samples, and continued LONG responses to guide learning. PaceReasoner combines all-response and LONG-only answer consensus through progressive, confidence-weighted supervision. A behavior reward gradually shifts from encouraging SHORT exploration to rewarding agreement with LONG answers, while a ratio controller regulates the balance between modes. Across three model backbones and four
benchmarks, PaceReasoner improves average SHORT accuracy over the baselines by 7.4–13.5 percentage points, with fewer than 25
reasoning tokens per response on average. Ablations support the key components, and cross-
dataset results demonstrate transfer beyond the adaptation set.
Read the full abstract ▾
All authors Changguo Jia, Zhiyou Xiao, Xinbei Ma, Geng Chen, Weiming Zhang, Yiming Xu, Tianqi Zhao, Minghui Zhou
Networking
Towards Virtual Networking for a Time-Triggered Hypervisor
Jan Ruh, Silviu S. Craciunas and Jan Korecky
Virtualization enables mixed-criticality applications to run on shared hardware by isolating them within separate virtual machines (VMs). However, achieving end-to-end timing guarantees for critical tasks hosted on virtual CPUs (VCPUs) without relying on static partitioning is hard. A possible solution is a time-triggered hypervisor that dispatches VMs' VCPUs to processor cores according to a predetermined global schedule. A global schedule includes the computation, the network, and the virtualization layer to provide end-to-end timing guarantees across hosts and VMs during design time. In this work, we propose a VirtIO-based virtual network that realizes IEEE 802.1Qbv quasi-compliant inter-VM communication, providing predictable timing for critical messages exchanged between time-triggered VMs. We present our VirtIO-based virtual network architecture and derive network-level scheduling constraints that emerge from the properties of the proposed solution. We implement the proposed design in the ACRN hypervisor and evaluate the end-to-end latency of critical traffic in a loaded network, demonstrating that our time-triggered VirtIO-net prototype provides predictable end-to-end latency under load.
Read the full abstract ▾
Machine Learning
Evaluating the Causal Faithfulness of SHAP as a Candidate Attribution Method for SAE Features
Samuel Xie and Noura Al-Moubayed
Sparse autoencoders decompose
language model representations into interpretable features, but feature interpretation in this literature remains predominantly correlational. Attribution methods offer more direct estimates of feature influence, yet their faithfulness to actual causal effects has not been systematically evaluated in the SAE setting. We apply SHAP-based attribution to SAE latent features and evaluate it against direct causal intervention, using sentiment classification on SST-2 with GPT-2 Small and a 32,768-feature layer-7 SAE as a testbed. We compare SHAP to Integrated Gradients, Gradient$\times$Input, and probe-weight baselines across linear and MLP probe arms, scoring each against feature ablation and activation steering measured through the
language model's own logit difference. Most faithfulness associations we measure do not survive multiple-comparison correction, and attribution methods that agree strongly with one another ($\rho = 0.42$–$0.80$) agree poorly with measured causal effects, indicating that inter-method agreement is not evidence of causal faithfulness. Two effects hold under control. First, local per-example attribution retains a directional advantage over global averaged attribution, while its apparent importance advantage is explained by feature activity rather than superior causal ranking. Second, under known-ground-truth minimal pairs, attribution recovers inserted sentiment signal well above chance (AUROC $0.792$) but fails to localize deletions (AUROC $0.520$), suggesting that these methods detect the presence of a feature's influence more reliably than its absence. We argue that importance faithfulness and directional faithfulness are separable properties requiring separate evaluation, and that attribution agreement should not substitute for causal validation.
Read the full abstract ▾
Information Theory
The Maximum Nonlinearity of 8-variable Balanced Boolean Functions is 116
Yueying Lou, Youle Xu and Qichun Wang
Does there exist an 8-variable balanced Boolean function with nonlinearity 118? This is a famous and long-standing open problem in Boolean functions. In this paper, we give a negative answer to this open problem, and prove that the maximum nonlinearity of balanced Boolean functions in 8 variables is 116, establishing the 8-variable instance of Dobbertin's conjectured recursion for the minimum Walsh peak of balanced functions. Equivalently, the covering radius of the Reed–Muller code RM(1,8) in 0-resilient Boolean functions is 116. We deduce the result by obtaining a quadratic form of polar rank 6, and reducing the problem to the existence of a 6-variable Boolean function with nonlinearity greater than 26 whose Hamming distance to a bent function is between 4 and 6.
Read the full abstract ▾
Machine Learning
Interaction-as-a-Judge
Wayne Chi, I-Hung Hsu, Li Chen et al. (+6 more)
Coding
agents are tasked with producing sophisticated interactive applications such as websites, desktop applications, and games. While humans assess these applications interactively, current automated LLM evaluations primarily focus on code analysis and unit tests. This mismatch can cause LLM judges to miss failures that are immediately apparent to human users. We study Interaction-as-a-Judge, an evaluation paradigm where computer-use
agents (CUAs) directly interact with an application. We demonstrate that Interaction-as-a-Judge can improve both evaluation and generation of interactive applications. To this end, we collect and release two complementary
datasets: $6,858$ pairs of applications with human preferences and corresponding
agent traces, and $222$ applications with human-verified requirement labels. Relative to standard non-interactive approaches, we find that Interaction-as-a-Judge improves evaluation in terms of predicting human preferences ($65.6\% \to 69.1\%$) and requirement verification ($77.0\% \to 81.6\%$). We also observe scaling benefits: across both preference
alignment and requirement verification, higher-quality interactions improve performance. Finally, through both inference- and training-time experiments, we demonstrate that Interaction-as-a-Judge can also improve the quality of generated artifacts. At inference time, Interaction-as-a-Judge repairs $75.5\%$ of broken requirements within five attempts, compared to $55.4\%$ for code-only self-feedback. At training time, using Interaction-as-a-Judge as a reward signal improves win-rate over the base model by $6.7$pp while reducing both generated code length by $35.7\%$ and build failure rates by $7.2$pp compared to a code-only reward signal.
Read the full abstract ▾
All authors Wayne Chi, I-Hung Hsu, Li Chen, Wei-Lin Chiang, Ion Stoica, Anastasios Nikolas Angelopoulos, Ameet Talwalkar, Chris Donahue, Cho-Jui Hsieh
Computation and Language
Swiss4Arg: A Parallel Dataset for Multilingual Argument Mining across Swiss National Languages
Sophia Conrad, Fatma-Zohra Rezkellah, Christina Niklaus et al. (+1 more)
We present Swiss4Arg, a multilingual
dataset for argument mining based on official Swiss voting brochures, covering all four national
languages: German, French, Italian, and Romansh (a Romance minority
language exclusively spoken in Switzerland). The brochures contain explicitly formulated arguments systematically organized into pro and con sections, resulting in a cross-lingually aligned resource with balanced argumentative stance. We create a
dataset that comprises 53 federal voting issues collected between 2019 and 2025, annotated for argument components (major claims, claims, premises, and non-argumentative units) and relations (support and attack) by three native speakers per
language. Inter-annotator agreement (Krippendorff's alpha) reaches 0.548 for component classification and 0.623 for relation and target classification, computed jointly across all annotators on the parallel data. We release both adjudicated labels and individual annotator annotations, enabling analyses of disagreement and cross-linguistic variation, and provide baseline results using GPT-5.4 and SwissBERT. Swiss4Arg establishes a novel
benchmark for multilingual argument mining, with a particular focus on cross-lingual comparability and low-resource settings such as Romansh. The
dataset and code are publicly available at https://anonymous-hf.up.railway.app/a/gozw0nion72y/ (HuggingFace) and https://anonymous.4open.science/r/MultiVote-03BD/ (GitHub).
Read the full abstract ▾
All authors Sophia Conrad, Fatma-Zohra Rezkellah, Christina Niklaus, Reto Gubelmann
Artificial Intelligence
Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards
Keru Chen, Sen Lin, Yingbin Liang et al. (+2 more)
Effective collaboration among large
language model (LLM)
agents in multi-
agent systems requires sharing relevant evidence, requesting missing information, and incorporating teammates' contributions into decisions. Training these behaviors is challenging because final task outcomes provide limited feedback on the value of individual messages. We introduce CoSIR (Collaboration via Surprisal-based Information Rewards), a post-training approach that uses a simple, verifiable environment to teach collaboration behaviors that generalize to more complex, unseen tasks. We propose a
Bayesian evaluator that scores shared information by its reduction in team surprisal, defined as the sum of the negative log probabilities assigned to the correct option given each
agent's available evidence. Requests are scored by the potential reduction in the same quantity if the requested information were truthfully provided. Separate rewards encourage
agents to use the received information in their private choices and calculations. We post-train Qwen3-4B, Qwen3-8B, and Gemma-3-4B-it through self-play and evaluate transfer to seven unseen natural-
language collaboration tasks. CoSIR achieves the highest aggregate score, while its performance in general tasks remains competitive. Behavioral analyses show increased disclosure of private evidence and fewer judged failures to use teammates' input.
Read the full abstract ▾
All authors Keru Chen, Sen Lin, Yingbin Liang, Nathaniel D. Bastian, Shaofeng Zou
Numerical Analysis
Provable Method of Moments for Cryo-EM
Amnon Balanov, Tamir Bendory, Dan Edidin et al. (+3 more)
We study the recovery of a three-dimensional volume in single-particle cryo-electron microscopy (cryo-EM) from noisy tomographic projections acquired at unknown viewing rotations, drawn independently and uniformly from $\mathrm{SO}(3)$. We show that, in a spherical-shell representation satisfying an explicit shell-separation condition, the first three moments generically determine the underlying real volume up to its intrinsic global $\mathrm{O}(3)$ ambiguity. The proof is constructive and yields a frequency-marching procedure that successively recovers the volume. Consequently, consistent recovery in the high-noise regime has sample complexity $n=\omega(\sigma^6)$, where $n$ is the number of observations and $\sigma^2$ is the noise variance. Numerical experiments validate the constructive recovery scheme under finite sampling and additive noise, and indicate that direct third-moment optimization can succeed beyond the structural assumptions required by the constructive proof.
Read the full abstract ▾
All authors Amnon Balanov, Tamir Bendory, Dan Edidin, Josh Katz, Shay Kreymer, Nir Sharon
Databases
Path Length Existence Problems in Bounded-Treewidth Probabilistic Graphs
Antoine Amarilli, Mikaël Monet and Harshul Sagar
We consider the problem of computing the probability of existence of a source-to-target path or walk satisfying a given length constraint in an input probabilistic graph. The length constraints we consider can require the length to be at least $\ell$, at most $\ell$, or exactly $\ell$, for $\ell$ a target length given as input. The probabilistic graphs that we consider are directed graphs where each edge is annotated with an independent probability of existence. As this task is generally intractable (#P-hard), we aim for
algorithms applying to input graphs that are assumed to be of bounded treewidth. We classify the complexity landscape of these problems: - We give an XP
algorithm parameterised by treewidth to compute the probability that an input probabilistic graph contains a source-to-target path/walk of length $\geq \ell$, and do the same for a path/walk of length $\leq \ell$. - We show that the four problems mentioned in the last item are W[1]-hard parameterised by pathwidth (hence not FPT under the standard assumption that FPT$\neq$W[1]). This is in contrast to the case of non-probabilistic graphs, where the corresponding problems were known to be FPT parameterised by treewidth; and to the connectivity problem (and more generally MSO evaluation) on probabilistic graphs, where the same was known. - Surprisingly, we show that it is #P-hard to compute the probability that an input graph contains a source-to-target path/walk of length exactly $\ell$, even on graphs of pathwidth $2$. By contrast, all our problems are tractable on graphs of treewidth $1$. - Last, we investigate the complexity of our problems when the edges can carry weights. This causes all our problems to become #P-hard already on pathwidth-2 graphs, and causes specifically the “exactly $\ell$” walk problem to be #P-hard even on pathwidth-1 graphs.
Read the full abstract ▾
Programming Languages
Compositional Information Geometry of Probabilistic Programs
Jacek Karwowski, Frank Nielsen and Sam Staton
We study the compositional, intensional information geometry of probabilistic programs. For a first-order probabilistic programming
language with finite random variables, we construct a contravariant lax monoidal functor that, for a program of type $X \to Y$, pulls back a (degenerate) Riemannian metric on $Y$ to $X$. It specialises to the Fisher metric in the case of standard statistical models and to ordinary pullback in the case of deterministic programs. We further justify this construction in two ways. First, we show that this functor arises as a pullback of geometry from a universal space of programs over a type $Y$ with a fixed trace space. Second, we show that it is a special case of a more general pullback construction over weighted measures. Our compositional geometry depends on the presentation of the program, and we study how it relates to the (non-compositional) geometry of the realised measures by establishing a three-level inequality relating our score-velocity metric for the program, the program's corresponding output-conditioned metric, and the standard Wasserstein-Fisher-Rao metric of the realised family. Finally, we show how the theory can be extended to accommodate continuous random variables using diffeological quasi-Borel spaces. We also discuss several concrete directions for future work.
Read the full abstract ▾
Machine Learning
Deep Mesoscopic Dynamics
Yue Zhao, Shiqi Wu, Yihang Ouyang et al. (+6 more)
Microscopic simulations resolve spatial patterns but are feasible only over small domains and short timescales, whereas bulk descriptions erase those patterns through spatial averaging. Mesoscopic fields preserve this spatial organisation, but their effective equations are known only for selected microscopic systems and scaling limits. We introduce Deep Mesoscopic Dynamics (DeepMesoD), which uses neural networks to learn an effective mesoscopic field equation from microscopic trajectories at a prescribed coarse-graining scale. For the nonconserved dissipative dynamics studied here, DeepMesoD learns the free-energy functional with a spatial interaction kernel and a state-dependent dissipation operator constrained by the fluctuation-dissipation relation. We first validate the construction in the Ising-Kac model, where the learned mesoscopic equation recovers the known hydrodynamic limit and rollouts remain stable far beyond the training horizon. We then treat two systems without closed-form mesoscopic descriptions. For a two-dimensional Heisenberg ferromagnet governed by atomistic
spin dynamics, DeepMesoD learns a mesoscopic model whose predictions match atomistic references up to 1 ns, and a rollout with an unseen initial condition remains bounded up to 25 ns. For layered CrBr$_3$, the learned kernel captures the suppression and sign reversal of interlayer coupling at a stacking fault whose location and strength are not supplied as inputs. Controlled changes to the learned interaction show how fault number and placement shape multistep
magnetic responses, complementing our magneto-photoluminescence measurements. Across the two atomistic systems, DeepMesoD achieves a three-to-four-order-of-magnitude reduction in wall-clock time compared with atomistic
spin dynamics.
Read the full abstract ▾
All authors Yue Zhao, Shiqi Wu, Yihang Ouyang, Sergey Grebenchuk, Magdalena Grzeszczyk, Xiaoxu Zhao, Kostya S. Novoselov, Maciej Koperski, Qianxiao Li
Computer Vision
Diagnose-to-Generate: Eliminating Structural Distortions in Flow Models via Patch-Level Grounded Alignment
Yifan Li, Lishuai Gao, Tong Zhang et al. (+8 more)
Flow-based image generators achieve strong semantic synthesis but still produce localized structural distortions, such as malformed hands and limbs. Existing post-training methods typically optimize global scalar rewards, which provide weak spatial credit assignment and may alter well-formed regions while correcting local defects. We present Diagnose-to-Generate (D2G), a grounded
alignment framework that separates visual diagnosis from generative optimization. We construct Achilles-600K, a region-annotated
dataset for structural anomalies, and train ARGUS through supervised cold-start and Region-Aware Group Relative Policy Optimization to predict anomaly categories and bounding boxes. These diagnoses are converted into confidence-weighted spatial rewards for our Patch-level Flow-GRPO. We further identify that global
stochastic exploration can shift semantic regions across group rollouts, making patch-wise relative advantages spatially inconsistent. Our Trajectory-Preserving
Stochastic Sampling (TPSS) anchors early denoising with deterministic ODE trajectories and introduces stochasticity only at later steps, thereby limiting intra-group spatial drift while retaining local exploration. Experiments on FLUX.1-dev and SD3.5 show improved structural fidelity with preserved FID and CLIP scores. Consistent gains under HumanRefiner, zero-shot GPT-4.1, and blinded human evaluation further demonstrate that the improvements extend beyond the training reward model.
Read the full abstract ▾
All authors Yifan Li, Lishuai Gao, Tong Zhang, Qilong Huang, Chen Zhao, Zhuoliang Kang, Jie Hu, Yujie Zhong, Fenghe Tang, S Kevin Zhou, Xiaoming Wei
Robotics
Agentic Robot Creation through Generation, Verification, and Revision
Xuebing Li, Yibo He, Sitong Liu et al. (+2 more)
Can an AI
agent turn high-level user intent into a functioning
robot and teach it how to behave? We study this question from two complementary aspects: embodiment and behavior creation. For embodiment creation, we investigate how well current
multimodal models capture mechanical requirements, and introduce computational metrics for evaluating generated designs before fabrication. For behavior creation, we present Roboforge, an agentic framework that turns task specifications into executable policies through motion generation, policy learning, and execution-grounded revision. Given a
robot embodiment and task, the
agent generates a reference motion, configures the learning objective, and trains a policy. Crucially, motion remains in the loop: rollout feedback can revise the reference motion, reward, or both. We evaluate a generated embodiment across multiple MLLMs and behavior creation across four diverse
robots against reward-refinement and one-shot motion baselines. Our computational metrics expose recurring mechanical failures in generated designs, while behavior experiments show that execution-grounded refinement improves task-level behavior and execution quality. Finally, we fabricate an
agent-generated Gorilla and directly deploy learned behaviors on the physical
robot.
Read the full abstract ▾
All authors Xuebing Li, Yibo He, Sitong Liu, Ran Ji, Jiayuan Gu
Computation and Language
Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric
Juann Kim and Minku Kang
Persona vectors are linear directions in the residual-stream activations of LLMs that encode behavioral traits and enable fine-grained control over model behavior. Among them, the evil persona vector is particularly relevant to understanding harmful behavior, jailbreak vulnerabilities, and the unlearning of harmful knowledge. Yet whether this vector reflects a genuinely cross-lingual concept, rather than an artifact of its extraction
language, remains untested. We conduct a systematic evil-vector transfer study across two high-resource
languages (English, Spanish) and two low-resource
languages (Swahili, Telugu) on four open-source instruction-tuned LLMs, and find that transfer is directionally asymmetric. Evil vectors are harder to obtain reliably from low-resource
languages, and the resulting vectors are largely ineffective at steering, even within their own
language. In contrast, vectors extracted from high-resource
languages transfer effectively to low-resource inputs while largely preserving general knowledge, as measured by MMLU.
Geometric analysis further supports this pattern: evil vectors from the two high-resource
languages are closely aligned, whereas low-resource vectors align only weakly with this shared direction. These results suggest that a shared cross-lingual evil direction exists and, once reliably extracted from a high-resource
language, can be reused to steer behavior in low-resource
languages without additional per-
language data collection.
Read the full abstract ▾
Computer Vision
LoopREG: Representation Supervision Enables Test-Time Recurrent Depth in Diffusion Transformers
Zipeng Wang, Anping Xiong, Jing Zhang et al. (+17 more)
Reusing
Transformer blocks offers a way to increase
diffusion-model computation at test time, but naive recurrence can degrade generation beyond its training depth. We introduce LoopREG, a representation-supervised recurrent
diffusion Transformer that repeatedly applies a shared block at the state supervised by a pretrained visual encoder.
Alignment is applied after the final recurrent visit during training; inference extends the same learned operator to additional visits. On ImageNet 256 x 256, LoopREG reduces SiT-B/2 FID from the local REG baseline's 15.08 to 4.91 at 400K training steps, a 67.41% reduction. Within a checkpoint trained with two visits, one extra inference visit improves FID from 14.71 to 5.34 with unchanged weights. The benefit persists on SiT-L/2 and SiT-XL/2. Controlled interventions show that useful recurrence follows the location of representation supervision, while REPA
alignment produces a smaller extrapolation benefit. These results make representation-supervised recurrence a practical route to improving
diffusion generation through additional inference depth.
Read the full abstract ▾
All authors Zipeng Wang, Anping Xiong, Jing Zhang, Xiaoya Zhu, Yi Jiang, Yanbing Xiao, Zige Zeng, Zezhou Chen, Xiang Liu, Huan Hu, Ping Chen, Kai Wang, Zhaoxiang Liu, Shiguo Lian, Ye LV, Fang Zhao, Huanlin Gao, Zhengrui Huang, Bo Shen, Yuren You
Machine Learning
Searching for What Matters: Open-Ended Discovery of Multiple Hypotheses with Agentic Data Exploration
Sanchit Kabra, Nurendra Choudhary, Jiangshu Du et al. (+3 more)
Discovering what drives an outcome from data is central to science and often requires deciding what is worth investigating before a specific hypothesis is known. Yet most existing hypothesis generation settings substantially narrow this search by providing a research question, target relationship, or curated context. We introduce open-ended multiple hypothesis discovery, where a system receives only a large tabular
dataset and an outcome and must discover multiple data-supported hypotheses without knowing in advance the relevant variables, functional forms, conditions, or number of underlying mechanisms. To study this problem, we introduce a
benchmark built from structural causal models grounded in real-world data schemas, containing 351 planted hypotheses across 15 tasks and five domains, with 53–65 variables and 1M–10M rows per task. The causal model is hidden from the discovery method and retained only by the evaluator, allowing proposed hypotheses to be tested through interventions and separating observational discovery from causal validation. We further propose HypAgent, which treats the
dataset as an interactive environment and performs iterative search by proposing candidate directions, triaging and refining promising hypotheses, and removing explained signal so that each accepted discovery redirects subsequent search. HypAgent achieves 0.47 precision, 0.51 recall, and 0.49 F1, compared with 0.35 F1 for the strongest baseline. Our analysis shows that many failures occur after a relevant variable has already been surfaced, suggesting that correctly characterizing a mechanism's functional form and conditions, rather than merely identifying relevant variables, remains a key challenge in open-ended discovery.
Read the full abstract ▾
All authors Sanchit Kabra, Nurendra Choudhary, Jiangshu Du, Eddie Huang, Danai Koutra, Chandan K Reddy
Robotics
Information-based Unified Design Framework for NMR Magnetic Tracking System
Seçkin Eren Yetim and Mehmet Efe Tiryaki
Nuclear
magnetic resonance (NMR)
magnetic tracking offers a promising alternative to
magnetic resonance imaging (MRI)-based localization for medical robotic guidance. However, scalar field measurements and field-aligned marker moments constrain position and orientation tracking, requiring careful configuration design. We present a unified information-based framework that uses local covariance analysis to evaluate receiver geometry, marker separation, and external source configuration in on/off-board NMR tracking. Numerical evaluation shows that planar-array precision depends jointly on receiver count and geometry, with triangular
lattice arrays achieving the lowest best-case position uncertainty among the evaluated layouts for 9–20 receivers. Two spatially separated, field-aligned markers enable device-axis tracking, with predicted angular uncertainty below $2^\circ$ at the evaluated workspace center for suitable marker separations. We further establish point-dipole source–receiver duality, unifying the analysis of on/off-board NMR tracking. These
Read the full abstract ▾
Software Engineering
Mobile App Analysis in the New Era: Challenges and the Road Ahead
Jiale Wu, Tianming Liu, Yanjie Zhao et al. (+1 more)
Mobile applications (apps) have grown into complex, multi-platform systems that support diverse services and operate within varying regulatory and distribution contexts. Traditional analysis techniques have established a strong foundation for ensuring quality, security, and compliance, but face increasing challenges as mobile apps evolve. This article presents a three-layer perspective to examine these challenges. The Artifact Layer highlights how heterogeneous code bases and protection mechanisms reduce the analyzability of packaged apps. The Runtime Layer addresses growing execution complexity, from multi-modal interactions and super-app architectures to AI-driven autonomous operations. The Ecosystem Layer considers broader contexts, including emerging platforms, fragmented distribution channels, and region-specific regulatory requirements. New characteristics across these layers interact and compound, creating difficulties that existing approaches are not designed to handle. For each layer, we identify key challenges and potential research directions, including framework-aware analysis, adaptive testing, and policy-aware compliance verification. We also discuss how large
language models bring new analytical capabilities to the field, while their integration into apps raises new security and
privacy concerns. This article aims to clarify where established methods fall short and highlight directions for future research in this evolving field.
Read the full abstract ▾
All authors Jiale Wu, Tianming Liu, Yanjie Zhao, Haoyu Wang
Information Theory
The Covering Radius of the Reed–Muller Code RM(1,9) is 242
Qichun Wang, Yueying Lou and Zifan Wang
What is the covering radius of the Reed–Muller code RM(1,9) ? This is a long-standing open problem in cryptography and coding theory. In this paper, we resolve this problem, and prove that the covering radius of RM(1,9) is 242. We exclude nonlinearity 244 by obtaining a cubic Boolean function achieving a sharp Walsh $\ell^1$ bound. Its equality cases reduce either to an impossible cubic hyperplane restriction or to two homogeneous cubic forms in the Brier–Langevin classification. To exclude nonlinearity 243, we deduce the inequality ${\Vert W_g\Vert }_{1}+2|W_g(0)|\le 10368$, and then reduce either to a spectrum bounded by 24 or to the same expression to be at least 10496.
Read the full abstract ▾
Robotics
LAG-IO: Multi-IMU State Estimation for Legged Robots Using Factor Graphs
Yicheng Zhou, Longwen Chen, Qinghua Yu et al. (+3 more)
Robust proprioceptive state estimation is crucial for legged
robots, particularly in challenging environments where exteroceptive sensors are unreliable. While traditional leg odometry typically relies on a single body-mounted inertial measurement unit (IMU) fused with leg kinematics via an extended Kalman filter (EKF), such methods are vulnerable to linearization errors and hard-contact assumptions, leading to severe drift during slippage or dynamic locomotion.In this paper, we propose LAG-IO, a factor graph-based multi-IMU state estimation framework that tightly couples measurements from a main body IMU, multiple leg-mounted IMUs, and joint encoders within a sliding-window optimization. To handle non-stationary foot-ground interactions, we introduce a continuous probabilistic contact detection module based on kernel density estimation (KDE), which adaptively scales the covariance of zero-velocity update (ZUPT) factors. Furthermore, kinematic relative position factors are formulated to structurally anchor the independent leg inertial states to the
robot's main body. Experimental results on a quadruped
robot across various unstructured terrains demonstrate that, compared to existing baselines, LAG-IO achieves higher planar trajectory accuracy, reduces unobservable vertical divergence, and provides smoother trajectory transitions during unstable contacts, while maintaining competitive attitude observability.
Read the full abstract ▾
All authors Yicheng Zhou, Longwen Chen, Qinghua Yu, Junhao Xiao, Huimin Lu, Xieyuanli Chen