Machine Learning
CopRoute: Dependence-Aware Conformal Routing for Language Models
Siva Rajesh Kasa, Santhosh Kumar Kasa and Karan Gupta
Set-based
language model routing aims to increase the coverage of the event where at least one model answers a query correctly while controlling the number of inference calls made. Existing risk-controlled routing policies bound the all-miss risk (the probability that every model in the selected set fails) by calibrating a single conformal threshold and applying it to a nested family of model sets. Because each model is scored in isolation, these policies ignore the dependence structure of model failures. Models that share training data or architecture tend to fail on the same queries, so two individually strong models can be jointly redundant while a weaker but complementary model covers the queries that the others miss. To account for this dependence, which existing risk-controlled policies ignore, we propose CopRoute, which orders models by how many new queries each one answers correctly beyond those already selected, decides per query how far down that order to go, and then picks the smallest cutoff that still meets the target risk. We show that CopRoute's ordering attains, on the design data, the best guarantee any efficient fixed-ordering
algorithm can give for the average number of calls to the first correct model, and that a separate calibration step certifies the all-miss risk of the deployed sets. On RouterBench and RouterEval, CopRoute attains the fewest certified calls on nine of ten
datasets at a target risk of 0.05 and on eight of ten at 0.10, making up to 79 percent fewer calls (median 24 percent) than the state-of-the-art risk-controlled policy at the same certified all-miss risk.
Read the full abstract ▾
Systems and Control · Cross-listed from q-bio.NC
Excitability across scales: a unifying EI model
Thomas S.J. Burger and Rodolphe Sepulchre
Neuronal excitability is commonly modeled using different principles at the cellular and population scales, making it difficult to study how microscopic mechanisms shape macroscopic activity. We introduce a spatiotemporal excitatory-inhibitory (EI) model that unifies these scales through a common mixed-feedback architecture. The model retains the conductance-based
circuit structure of Hodgkin-Huxley models and describes intrinsic and synaptic currents through memductances whose temporal and spatial voltage dependence encodes dynamics at the relevant scale. In its minimal form, temporal excitability arises from fast excitatory feedback opposed by slower inhibitory feedback, while spatial excitability arises from short-range excitation opposed by longer-range inhibition, recovering the core lateral-inhibition motif of Amari neural fields. We show that combining these mechanisms gives rise to population excitability in strongly heterogeneous populations. In particular, the model generates population spikes that are localized in both space and time and possess population-level scales distinct from those of individual neuronal spikes, despite substantial
cell-to-
cell parameter variability. We then show that both intrinsic temporal excitability and spatial synaptic feedback are required for coherent mean-field events and robust spatiotemporal population rhythms. Finally, selective modulation of memductances in a subset of the population tunes the frequency of the population rhythm, illustrating how changes at the cellular scale can shape macroscopic dynamics. By separating
circuit architecture from modeling scale, the proposed framework provides a physically interpretable approach to analyzing and designing neuronal excitability across scales.
Read the full abstract ▾
Formal Languages and Automata
Prime Accessible Deterministic Automata
Shen Zhao and Chenghe Xu
We classify
prime accessible deterministic automata over finite alphabets, both among finite automata and among automata with arbitrary state sets. Every one-state automaton is
prime. Over a one-letter alphabet, a finite nontrivial automaton is
prime exactly when it is a cycle of
prime-power length or a finite chain ending in a fixed state. The unique infinite accessible unary automaton, up to isomorphism, is also
prime. Every nontrivial automaton over an alphabet with at least two letters is not
prime. Shen proved the finite case; we give a shorter proof. We also characterize a decomposition of the automaton whose states are all finite input words. The reachable product of the quotients by the least right congruences identifying the empty word with nonempty words $p$ and $q$, respectively, is isomorphic to this automaton exactly when $p^r\ne q^s$ for all positive integers $r,s$.
Read the full abstract ▾
Software Engineering
Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis
Yongjian Tang, Costel Moraru, Doruk Tuncel et al. (+3 more)
API specifications serve as critical documentation for modern software development, directly impacting integration efficiency and client code generation. While recent advancements have leveraged Large
Language Models (LLMs) to generate initial specifications from source code, existing approaches treat this process as a one-time event - overlooking the needs for continuous validation, long-term maintenance, and
market-driven
evolution of these artifacts. To address this issue, we present
Agent4Spec, an autonomous multi-
agent framework featuring two distinct pipelines: (1) a validation pipeline that detects and self-corrects OpenAPI syntax errors, and (2) a
market analysis pipeline that conducts competitive research, identifies functional gaps against industry leaders, and automatically generates missing API-spec functionalities. We evaluate
Agent4Spec on two curated
datasets of API specifications spanning both general-purpose and industrial scenarios. Among 9 SOTA LLMs, the top-performer achieves 100% syntax error detection rates and over 95% implementation success for proposed corrections, while securing over 50% adoption rates for suggested endpoint improvements, representing a practical tool for API development.
Read the full abstract ▾
All authors Yongjian Tang, Costel Moraru, Doruk Tuncel, Hanya Elhashemy, Steffen Klepke, Thomas Runkler
Computer Vision
OWLET: On-Policy Weighted Learning via Evidence Transfer for Video Large Language Model Post-Training
Qitan Lv, Ke Fan, Hong Wang et al. (+5 more)
Post-training has become a key stage for eliciting
reasoning capabilities in
Video Large
Language Models (
Video-LLMs). Existing post-training methods mainly follow two paradigms: reinforcement learning (RL) and on-policy
distillation (OPD). However, they do not fully exploit visual evidence for effective training. RL supervises the policy with a single trajectory-level reward, which is too coarse-grained for
video reasoning: the same response-level advantage is applied to every generated
token, disregarding that the
tokens of a
video response are grounded in the visual stream to very different degrees. OPD provides
token-level supervision through output-distribution matching, but lacks direct supervision of the spatiotemporal representations that produce those outputs. We observe across extensive experiments that the same model reasons more accurately when its
video view combines global temporal context with question-relevant details. Comparing the same student-generated response under this view and uniform sampling reveals changes in
token likelihoods and internal representations, providing a training signal for evidence use. Building on this observation, we propose OWLET, an evidence-privileged RL method that derives training signals from a richer teacher view. This view couples uniform global context with question-conditioned local windows, providing visual evidence without requiring a larger model. To better exploit this privileged visual evidence, OWLET introduces (i) evidence-aware credit redistribution, which compares
token likelihoods across the two views and redistributes positive response-level advantages according to their relative evidence support; and (ii) spatiotemporal state
alignment, which aligns the two views' hidden states on verifier-accepted responses.
Read the full abstract ▾
All authors Qitan Lv, Ke Fan, Hong Wang, Wen Wu, Yilin Wang, Bowen Zhou, Feng Wu, Chao Zhang
Data Structures and Algorithms
Polynomial directed treewidth forces a large bramble with congestion two
Victor A. Campos, Raul Lopes, Rodrigo Nogueira et al. (+1 more)
Brambles of constant congestion in directed graphs have interesting structural and algorithmic applications, and it is desirable to find the smallest function $f_c(k)$ such that if a digraph has directed treewidth at least $f_c(k)$, then it contains a bramble of size at least $k$ and congestion at most $c$. By the Directed Grid
Theorem of Kawarabayashi and Kreutzer [STOC 2015], such a function $f_c(k)$ exists for every value $c \geq 2$ of the congestion. However, even using the recent improvements due to Hatzel et al. [FOCS 2024], the resulting function is a power tower of height $22$. Recently, Masařík et al. [SIAM J. Discrete Math. 2022] proved that, for congestion $8$, the function $f_8(k)$ can be made
polynomial; more precisely, they showed that $f_8(k) = \mathcal{O}(k^{48} \cdot \log^{13} k)$. They asked whether it is possible to decrease the congestion, ideally to $2$, even at the cost of a higher
polynomial function. In this work we answer their question affirmatively with the best possible value of the congestion, by proving that $f_2(k) = \mathcal{O}(k^{96}\cdot \log^{23} k)$. We also obtain smaller
polynomials for higher congestion, namely $f_4(k) = \mathcal{O}(k^{72} \cdot \log^{21} k)$ and $f_6(k) = \mathcal{O}(k^{66} \cdot \log^{18} k)$. Our results are inspired by the proof for congestion $8$, which we improve by introducing walkages. Walkages allow us to avoid technicalities of the original proof by translating ideas due to Reed and Wood [Eur. J. Comb. 2012] that work for undirected graphs to the directed setting. Our proofs are constructive and naturally yield
polynomial-time
algorithms to find the brambles assuming a certificate for large directed treewidth is given. Moreover, we discuss algorithmic applications of our results for the Directed Disjoint Paths with Congestion problem, and to half-integral packings of subgraphs with large directed treewidth.
Read the full abstract ▾
All authors Victor A. Campos, Raul Lopes, Rodrigo Nogueira, Ignasi Sau
Computer Vision
ConClick: Element-Wise Contrastive Learning Improves GUI Grounding
Ruotian Zhang, Yuhui Zhang, Junzhe Huang et al. (+3 more)
GUI grounding, the task of locating the interface element specified by a user instruction, is a fundamental capability of GUI
agents. However, existing grounding models remain error-prone, often causing downstream task failures. We systematically evaluate 10 grounding models across five
datasets and identify a major error pattern: most incorrect clicks hit non-target interface elements rather than the background, with different models repeatedly selecting the same distractors. Motivated by these findings, we propose ConClick, a contrastive learning framework that teaches models to distinguish the target element from plausible distractors. We construct ConClick-Data, a
dataset containing 4,292 challenging target-distractor pairs, and train the model using complementary listwise ranking and pairwise margin objectives. ConClick improves the grounding accuracy of Qwen3-VL-8B from 54.71% to 66.03% on ScreenSpot-Pro, from 83.72% to 86.28% on MMBench-GUI L2, and from 63.33% to 70.20% on OSWorld-G, outperforming prior methods built on the same or similarly sized backbones. We further introduce ReClick, an inference-time strategy that revisits promising regions and compares predictions across competing candidates, yielding an additional 2.96 percentage-point improvement in average accuracy across the three
benchmarks. Together, our analysis,
dataset, and methods provide both empirical insights and practical tools for building more reliable GUI
agents. Data and code are available at https://github.com/zhangruotian/ConClick.
Read the full abstract ▾
All authors Ruotian Zhang, Yuhui Zhang, Junzhe Huang, Yu Xin, Hehe Fan, Xiaoxiao Sun
Artificial Intelligence
Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
Lei Liu, Yunji Liang, Xiaowen Zhang et al. (+4 more)
Large
language model (LLM)
agents are highly vulnerable to
memory-poisoning attacks. Existing defenses primarily rely on external modules for either static
memory isolation or continuous online auditing, resulting in low
memory efficiency and high computational overhead. To address these limitations, inspired by neuroscientific mechanisms that weak reactivation can destabilize
memories and induce decay in the absence of reinforcement, we propose an
agent-intrinsic training-free
memory repair framework, DREAM (Dynamic Reactivation for Engram Attenuation in
Memory), that enables selective functional forgetting of poisoned
memories. Specifically, DREAM implements a three-stage pipeline: perturbation-induced implicit reactivation to reveal the structural fragility of malicious
memories, adaptive anomaly diagnosis based on multi-dimensional activation patterns to detect topological anomalies, and a dynamic
memory repair module that selectively suppresses harmful
memories while reinforcing benign ones. Extensive experiments across diverse attackers and real-world tasks demonstrate that DREAM reduces attack success rates by over 95% against backdoor poisoning while preserving strong benign utility. DREAM also achieves competitive robustness against injection attacks. In terms of runtime and
token consumption, DREAM achieves up to a 2.13$\times$ speedup and a 37.7% reduction in
token consumption compared with A-MemGuard. Furthermore, DREAM also achieves a task success rate of 92.96% on poisoned multi-
agent systems.
Read the full abstract ▾
All authors Lei Liu, Yunji Liang, Xiaowen Zhang, Jingqi Liu, Qi Li, Bin Guo, Zhiwen Yu
Computer Vision
Haowei Wang, Hao Lin, Qi Zhu et al. (+4 more)
On-policy
distillation (OPD) reveals versatility and convenience during VLM post-training, providing dense supervision for student from teacher. However, we observed an anomaly that the distilled VLM could still answer the questions accurately even when the related visual regions were masked or replaced with noise. Building on this observation, our quantitative and qualitative experiments demonstrate that OPD, which uses the answer as a hint, has failed to teach students to genuinely seek out and rely on visual evidence. Our theoretical analysis suggests that this failure arises from a shortcut enabled by the lack of visual constraints during
distillation. To address the issue, we introduce Contrastive
Vision On-policy
Distillation (CV-OPD), which compares teacher distributions induced by positive and negative crops while conditioning on the same student prefix and augments optimization with a margin-based contrastive constraint, which is modulated with discrepancy gating across
token and sample level. Specifically, CV-OPD first introduces a negative teacher unrelated to the answer and designs a Contrastive Divergence Loss (CDL) that constrains the feature distribution of student by contrasting the positive and negative teachers, correcting how the student exploits visual regions. The CV-OPD introduces a Discrepancy Aware Gate (DAG) that uses
token-level and sample-level discrepancies to select visually relevant
tokens for optimization, directing the student's
attention toward visual content. Extensive experiments across a broad range of fine-grained visual
benchmarks demonstrate that CV-OPD substantially alleviates shortcut and consistently improves the visual
reasoning capabilities of existing VLMs.
Read the full abstract ▾
All authors Haowei Wang, Hao Lin, Qi Zhu, Jiayi Ji, Deyi Ji, Liujuan Cao, Rongrong Ji
Computer Vision
SheafPrune: Sheaf-Guided Graph Propagation for Visual Token Pruning
Xiaoyang Ma, Chi Wang and Hong Sun
Multimodal large
language models process the complete visual
token sequence, increasing prefill cost even when many
tokens are irrelevant to the instruction.
Token-wise saliency captures limited inter-
token dependence; graph-based selection instead depends on how relations govern importance propagation and ranking. We study support-constrained propagation with node-degree correction. Inspired by sheaf geometry, SheafPrune uses modality-specific maps and a sparse text–visual graph to transfer relevance, then propagates scores on a separate visual graph and corrects them for degree. It retains a hard top-$k$ subset once before the frozen
language model. The selector has about $4.5$M parameters and is trained end-to-end through the frozen LLaVA-NeXT-8B backbone using only the
language-modeling objective. Explicit retention-ratio conditioning lets one checkpoint serve every budget. Across four backbones, ten
benchmarks and seven
pruning ratios, with all baselines re-implemented under one protocol, SheafPrune achieves the best retention at $22$ of $28$ backbone–budget settings, with monotonically growing margins in the moderate-to-aggressive regime. On LLaVA-NeXT, retaining $10\%$ of visual
tokens yields a $5.15\times$ net prefill speedup and an $84.0\%$ end-to-end FLOPs reduction. Together with component ablations, these results support graph-constrained importance propagation and degree correction as a design for visual
token selection across the evaluated backbones and tokenization schemes, improving the trade-off between accuracy retention and inference cost. code:https://github.com/Bob0817912/SheafPrune_ICLR_2027
Read the full abstract ▾
Robotics
Yang Wang, Ping Liu, Ruiyu Wang et al. (+3 more)
Memory-dependent manipulation requires a policy to track execution state and recover visual evidence that is no longer observable. We propose dual-stream
memory for
vision-
language-action policies, assigning these requirements to complementary representations. A task-agnostic Gated DeltaNet compresses history into one temporal
token, supervised by progress prediction and action-conditioned feature reconstruction. A task-conditioned retriever retains frames above a fixed relevance threshold; linear multi-scale fusion encodes each frame into sixteen spatial
tokens. We then freeze the temporal compressor and jointly optimize
retrieval and policy learning. Across sixteen RoboMME tasks, the complete model achieves 49.22% mean success versus 44.51% for the published FrameSamp+Modul reference, improving fourteen tasks and all four suite means. On four real-
robot tasks, mean success reaches 62.5% versus 37.5%, with the largest gains on repeated actions requiring execution-stage discrimination. These results support combining execution context with selective visual access, while failures under cup swaps expose persistent identity tracking as an unresolved requirement.
Read the full abstract ▾
All authors Yang Wang, Ping Liu, Ruiyu Wang, Xuhua Chen, Lingfeng Zhang, Tao Zhang
Machine Learning
Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers
Zhenke Duan, Xin Li, Jiqun Pan et al. (+3 more)
In this paper, we propose Data-Adaptive Mahalanobis Cross-Head
Attention (DAMCHA), a simple and effective
attention mechanism that generalizes Multi-Head
Attention (MHA) through the lens of metric learning. Standard MHA implicitly learns a static, head-wise Euclidean similarity corresponding to the diagonal blocks of a unified cross-head metric
matrix, discarding all off-diagonal interactions across heads. DAMCHA addresses this limitation via two key innovations. First, it learns the full cross-head metric
matrix, inducing a Mahalanobis-like similarity that explicitly captures inter-head interactions beyond the restricted block-diagonal structure of MHA. Second, it parameterizes the metric
matrix as an input-dependent function, enabling the
attention geometry to dynamically adapt to the intrinsic
manifold structure of the data rather than remaining fixed after training. We further introduce principled regularization strategies, most notably stack-wise parameter sharing, to ensure computational efficiency and stable optimization. DAMCHA serves as a drop-in replacement for MHA and its variants in various
Transformer architectures, delivering superior expressive power and learning performance with comparable or reduced computational overhead. Extensive experiments demonstrate that DAMCHA-based
Transformers consistently outperform competing baselines across a range of
benchmark tasks. Code is available at https://github.com/erwinmsmith/DAMCHA.
Read the full abstract ▾
All authors Zhenke Duan, Xin Li, Jiqun Pan, Dong Xiaofei, Hanwen Ning, Xinyuan Song
Computer Vision
Beyond a Single Crop: Contextualized Embeddings for Player Re-Identification
Ge Luo, Changhuo Yang, Weisi Fan et al. (+2 more)
Person re-identification is typically addressed by learning identity-discriminative
embeddings from individual person crops. However, player re-identification in broadcast sports
videos presents a unique challenge: players from the same team often share similar appearances, while
video sequences provide repeated observations of the same players under different viewpoints and surrounding contexts. Existing crop-based approaches largely ignore this contextual information, which can be critical for resolving visually similar identities. Here, we propose ContextReID, a contextualized
embedding framework that represents a player by jointly considering other players in the same frame and observations from different frames of the broadcast sequence. By incorporating both co-occurring players and cross-frame observations, the model learns identity features relative to the surrounding visual context rather than relying only on isolated appearance cues. We implement this framework with a
vision-
language model that takes sets of player crops as input and generates context-aware
embeddings for individual players. A combined contextual learning and
retrieval objective encourages the model to capture cross-frame identity relationships while maintaining discriminative
embeddings for player matching. Experiments across three multi-object tracking
benchmarks show that ContextReID improves player
retrieval over conventional single-crop
embedding approaches in both Rank-1 and mAP. These results highlight the utility of spatial and temporal context for reliable player identification in broadcast sports
videos.
Read the full abstract ▾
All authors Ge Luo, Changhuo Yang, Weisi Fan, Rui Yang, Shaokai Wang
Machine Learning
Neural Surrogate Modeling of Ultrasonic Wave Propagation in Heterogeneous Media
Burla Nur Korkmaz, Petro Moilanen, Ari Salmi et al. (+2 more)
Neural surrogates provide computationally efficient auto-regressive modeling of wave propagation, enabling e.g. fast inverse solutions. Despite recent progress, the current surrogates are not yet sufficient for the needs of ultrasonic sensing, characterized by high frequency and heterogeneous propagation media. We show how methods building on
Fourier Neural Operators (FNO) fail to capture essential signal features, such as reflections, whereas U-Net -based methods learn the wave fields well but lack the ability to transfer information across different spatial scales. We then propose a new surrogate that captures the best of the two worlds, by integrating FNOs and local-integral resampling into a U-Net architecture. We show it can be trained on limited data, and that the predictions are robust to input noise and work across spatial scales.
Read the full abstract ▾
All authors Burla Nur Korkmaz, Petro Moilanen, Ari Salmi, Harsha Vardhan Tetali, Arto Klami
Machine Learning
CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation
Jingru Yang, Jinhang Wu, Minjing Shi et al. (+4 more)
Cross-tokenizer on-policy
distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text
alignment provides such correspondence at the chunk level, but leaves a distinct problem unresolved: credit
alignment. A chunk-level signal specifies how much a span should change, but not how that signal should be distributed across student
tokens, while
tokens without teacher correspondence remain unconstrained. We propose CAST (Chunk-aware credit Assignment with Selective
Token Anchoring), a shift-or-stay framework that addresses both issues. For aligned chunks, CAST redistributes each chunk's advantage across student
tokens using predictive uncertainty and local teacher-signal smoothness, emphasizing learning opportunities supported by locally consistent teacher feedback while preserving the chunk's total advantage. The resulting weights exactly solve a KL-regularized credit-allocation problem. For unaligned positions, CAST selectively anchors the student to its initial policy through a KL penalty, limiting drift where teacher supervision is unavailable. Because credit assignment is separated from chunk construction, CAST also applies to punctuation-defined or fixed-length chunks under shared tokenization. Across six mathematics, science, and code
benchmarks, CAST improves the average over the strongest evaluated baseline by $2.45$ and $1.32$ points for cross-tokenizer transfer from Qwen3-8B to Mistral-7B and Llama-3.1-8B, respectively, and by $2.10$ points for shared-tokenizer transfer to Qwen3-1.7B.
Read the full abstract ▾
All authors Jingru Yang, Jinhang Wu, Minjing Shi, Shengfeng He, Xuyan Li, Man Tan, Biye Li
Machine Learning
Tabular Foundation Models Are Effectively Shallow
Irene Cannistraci and Julia E. Vogt
In-context-learning Tabular Foundation Models (TFMs) are uniquely suited to scenarios with limited resources or
privacy constraints, as they solve new tasks without additional training. However, their architecture consists of multiple
transformer blocks, resulting in high computational and
memory footprints. Meanwhile, traditional alternatives like Gradient-Boosted Decision Trees (GBDTs) remain highly competitive and run efficiently on CPUs, suggesting that tabular tasks may not inherently require deep architectures. This contrast raises a fundamental question: can TFMs be simplified by removing architectural redundancies without sacrificing performance? To answer this, we introduce a closed-form, label-free affine translator that replaces a contiguous window of up to 96% of the blocks, leaving the rest unchanged. Evaluating eight frontier TFMs on 171 classification
datasets, we reveal that tabular
transformers are vastly overparameterized: replacing half of a model's blocks costs at most $0.002$ median AUROC across all architectures, with the half-depth TabFM still outperforming every other full-depth TFMs and tuned GBDTs. Furthermore, different model families are overparameterized in different ways: TabPFN-3 relies on its encoders, maintaining performance regardless of which single block is retained. Other single-axis models spread computation thinly, needing only their first block, while dual-axis models concentrate it in one critical block. Ultimately, removing depth saves up to 1.5B parameters, speeds up GPU inference by up to $6\times$ at a median cost of $0.03$ AUROC, while a single-block TabPFN-3 serves cached queries $2.4\times$ faster using $6\times$ less
memory at negligible cost.
Read the full abstract ▾
Computer Vision
Vision Transformers Learn Word Meaning from Images Alone
Anders Gjølbye, Sebastian Ray Mason, Stella Frank et al. (+1 more)
Can a
vision model learn what words mean from pixels alone? We show that the two largest DINOv3
vision transformers organize words rendered in images by word meaning, despite being pretrained using self-supervision on images only, without paired captions, class labels, or other
language supervision. We derive word representations from
embedding differences between word images and matched controls, then test whether semantically related words are neighbors within each model's
embedding space, while controlling for spelling similarity. We find that brand names in the same industry group together, as do nouns from the same semantic domain. Country-capital pairs exhibit consistent vector offsets, similarly to word
embeddings trained on text. These word representations also align with the representations of the visual object categories they name. DINOv3-H and DINOv3-7B are, to our knowledge, the first self-supervised
vision models to show substantial semantic structure for rendered words. Comparisons with text and
speech encoders reveal shared structure among representations of the same words. Contrastive
alignment with either encoder further strengthened DINOv3-H's word-level semantic structure, while leaving the other finetuned
vision models largely unchanged. Image-only training can therefore teach
vision models not just what words look like, but also how their meanings relate.
Read the full abstract ▾
All authors Anders Gjølbye, Sebastian Ray Mason, Stella Frank, Lars Kai Hansen
Databases
CALQA: Conformal Screening of Forecast-Ensemble Configurations from One Mergeable State
Xiufeng Liu, Ruyu Liu, Yusen Liu et al. (+2 more)
AutoML systems fit ensemble weights over model libraries; a search can score, per category,
market or time pane, thousands of weightings of the
quantile-averaged (Vincentized) ensemble for the narrowest conformally calibrated interval; exact calibration scores a group's rows per candidate. We present CALQA, a fixed-size integer aggregate per group and pane that stores histograms of normalised block scores at a net of weight vectors. One GROUP BY builds it; it merges by addition, retracts deletions by subtraction and scores any candidate without reading a row. We prove that its score never falls below the exact split-conformal shift and exceeds it by at most the net distance plus a grid gap; that coverage carries over to each fixed weight vector and, for i.i.d. blocks and up to a union-bound slack, to a searched weight vector deployed with the state's shift; and how small any such state can be. The state is thus a screen: it ranks all candidates, and exact recomputation re-checks the top 100. On five public panels (604 groups, 10,000 candidates each) this two-stage plan matches exact search on held-out blocks (99.95% of its Winkler score), 1.3-59 times faster. On two real panels of about $10^8$ rows (smart meters, retail sales) it is 44-54 times faster at 99.98-100.01% of that score and beats sample screens with the same re-check in regret at less total time. Picks deployed with their exact shift need a held-out coverage check. The state does not pay off for small or greedy searches, off-net weights at ample
memory or full twelve-member support.
Read the full abstract ▾
All authors Xiufeng Liu, Ruyu Liu, Yusen Liu, Huan Huo, Per Sieverts Nielsen
Sound
What Do Audio-Language Judges of Generated Music Listen For? Four Probes with Controls from Expert Ratings
Mateusz Modrzejewski and Tomasz Radzikowski
Open audio-
language models are used as judges of generated music: given a clip and its text
prompt, the model rates the clip, and the judge is validated by how well its ratings correlate with expert ratings. The correlation does not show what the judge responds to: the music, the text
prompt, or the way the question is asked. We propose four probes that test each of these, three of them read against a control computed from the human ratings: removing the audio, replacing the clip with another model's clip for the same
prompt, swapping the order of two clips in pairwise judging, and rewording the instruction. We apply them to five open judges on all 2,748 clips of MusicEval, and the last two to the SongEval songs. Without audio, no judge exceeds what the
prompt alone predicts from the human ratings, and for
prompt alignment every judge falls below it. With audio, every judge follows the clip it hears when rating
prompt alignment, two do when rating musical quality, and the strongest judge's quality score tracks the experts'
alignment rating more than their quality rating. The pairwise verdicts of the four smaller judges follow the position of a clip in the pair (its slot) rather than its quality on both rating sets. For musical quality, rewording the instruction moves the correlation of most judges as much as changing the judge. MusicEval's
prompt assignment bounds any
prompt-only judge at the model level. We recommend reporting the four probes with every music judge.
Read the full abstract ▾
Numerical Analysis
ADER-ZIST - a mixed explicit ADER-DG and zonally implicit space-time DG approach for Cartesian cut cell meshes
Michael Dumbser, Christian Engwer, Sandra May et al. (+1 more)
We present high order accurate mixed explicit-implicit discontinuous Galerkin (DG) schemes for the solution of
hyperbolic systems of conservation laws on Cartesian cut
cell meshes. Such meshes may contain arbitrarily small cut
cells, which leads to the well-known small
cell problem: the CFL condition of explicit schemes would severely restrict the admissible time step. To overcome this difficulty, we use high order explicit fully-discrete one-step ADER-DG schemes only on Cartesian
cells away from the embedded boundaries. The zone close to the embedded boundary, which consists of cut
cells and their direct face neighbors, is discretized with an implicit space-time DG scheme that is coupled to the explicit scheme directly via the numerical flux. The resulting scheme, called ADER-ZIST (ADER-DG with Zonally Implicit Space-Time DG), is conservative by construction, and its time step is determined only by the size of the Cartesian background
cells. Curved embedded boundaries are represented by high order isoparametric sub-triangles inside the cut
cells, and the nonlinear system of the implicit
cells is solved via an inexact
matrix-free Newton-Krylov method. For problems with shock waves, we add an artificial viscosity term whose strength is controlled by an oscillation-eliminating smoothness sensor. ADER-ZIST is assessed on a comprehensive set of test problems for the compressible Euler equations, ranging from smooth flows around straight and curved embedded boundaries to acoustic scattering and shock-dominated flows. The scheme essentially reaches its nominal order of accuracy N+1 for smooth solutions and for
polynomial degrees up to N=5, on meshes with minimal volume fractions of the small cut
cells down to the order of 10^-7.
Read the full abstract ▾
All authors Michael Dumbser, Christian Engwer, Sandra May, Peter Munch
Discrete Mathematics
Equitable Subpartitionability Does Not Characterize Box-TDI Polyhedra
Emiliano Lancini and Francesco Pisanu
Equitable subpartitionability (ESP) is a sufficient condition for an integral system to be box-totally dual integral. We show that the converse fails even when alternative descriptions of the same polyhedron are allowed. We provide a geometrical characterization of polyhedra that can be described by ESP systems in terms of normal cones. We construct a four-dimensional integer polytope described by a totally equimodular
matrix that admits no integral ESP description. This answers negatively a previously posed question by the same authors.
Read the full abstract ▾
Computer Vision
Deep Learning Approach for RealTime Contraction Detection in Laboring Dairy Cattle
Sebastian Puchala, Dominik Gronkiewicz, Marcin Gołębiewski et al. (+2 more)
Currently, the animal production sector is undergoing rapid development of techniques that allow automatic monitoring of animal behaviour and health. This paper presents a computer
vision-based approach for the automatic recognition of labor contractions in cows. During the course of the study,
videos depicting 100 cow births were collected. From the obtained
videos, 8500 cow contraction actions and about 25 000 non-contraction sequences were extracted which constituted the
dataset. Leveraging image processing techniques and deep learning
algorithms like Convolutional Neural Networks (CNNs) and
Vision Transformers (ViTs), our methodology extracts relevant features from
video frames to detect and classify contractions. Our study demonstrates a high accuracy rate of over 95% in detecting labor contractions. This automated system has the potential to enhance productivity and animal welfare in the dairy industry by providing real-time monitoring and facilitating timely intervention during difficult calvings. The
video demonstration of the system can be found at the following URL: https://www.youtube.com/watch?v=8fTSG5D7dZ0
Read the full abstract ▾
All authors Sebastian Puchala, Dominik Gronkiewicz, Marcin Gołębiewski, Grzegorz Grodkowski, Grzegorz Gwardys
Computer Vision
Jag: Direct Box Prediction for Efficient Visual Grounding
Xiuyuan Zhu, Ke Lu, Hao Wu et al. (+3 more)
Visual grounding combines image–
language understanding with
geometric prediction, yet autoregressive
multimodal models often express a box as a coordinate sequence. Sequential decoding adds computation to the
multimodal processing needed for localization. Adapting these representations to box geometry offers a route to direct prediction. We present Jag, which adapts a compact pretrained
multimodal model for direct continuous box prediction. A lightweight regression head reads the last valid input-
token state, conditioned on the image and referring expression, and predicts all four box coordinates together.
Geometric supervision jointly adapts the
language backbone, visual merger, and regression head, allowing localization losses to shape both the
multimodal representations and the coordinate mapping. Inference retains image–
language processing and returns the box in one forward pass, without coordinate generation or text parsing. Across
benchmarks, Jag consistently improves grounding accuracy over its base model across the observed target sizes and expression groups. Component ablation show that jointly adapting the representations and head substantially improves accuracy over training the head alone. Against existing specialized grounding models, it achieves competitive accuracy with lower single-request latency and GPU
memory use. These results show how supervision tailored to the
geometric answer can specialize a compact pretrained
multimodal model for accurate grounding and efficient direct prediction. Project page: https://xyzzzh.github.io/Jag/
Read the full abstract ▾
All authors Xiuyuan Zhu, Ke Lu, Hao Wu, Zijin Du, Dongming Zhang, Jian Xue
Machine Learning
State-OPD: State-Grounded On-Policy Distillation for Multi-Turn Agents
Zhentao Zhang, Yanzhao Zheng, Yanlin Liu et al. (+9 more)
On-Policy
Distillation (OPD) has emerged as a powerful paradigm for transferring
reasoning capabilities from frontier models to smaller models, while extending its success to multi-turn agentic environments remains challenging. We study agentic OPD through interaction states, distinguishing the objective task and executed action-observation record from the internal semantic trajectory of student
reasoning. Through this lens, we identify two roles of student
reasoning in multi-turn OPD: prior
reasoning distorts teacher supervision, while current
reasoning shapes the action alternatives sampled at the same state. Specifically, at matched interaction states, removing prior student
reasoning improves teacher continuation success and changes the teacher's
token-level targets, with larger continuation gains at later turns. Meanwhile, resampling complete
reasoning-action responses yields greater action diversity at the same state than resampling actions under a fixed
reasoning trace. We introduce State-Grounded On-Policy
Distillation, a framework that grounds teacher supervision in interaction states and reallocates the sampling budget to generate multiple complete
reasoning-action responses at states with high response
entropy, while retaining full-history student generation. Comprehensive evaluations across ALFWorld, ScienceWorld and WebShop demonstrate that State-OPD achieves the highest macro-average success rate among the evaluated methods for both Qwen3-1.7B and Qwen3-4B students. Notably, for Qwen3-4B, State-OPD raises macro-average success from 26.07% with the strongest baseline to 31.74% and surpasses its Qwen3-32B teacher on ALFWorld Seen. Further analyses reveal that State-OPD achieves higher task success with fewer supervised turn responses and substantially reduces persistent failed-action repetition; qualitative traces illustrate decision revision based on interaction feedback.
Read the full abstract ▾
All authors Zhentao Zhang, Yanzhao Zheng, Yanlin Liu, Yuanqiang Yu, Tianze Xu, Chao Ma, Jihuai Zhu, Lelun Wu, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu
Computer Vision · Cross-listed from eess.IV
The Predictability Bias of Joint-Embedding Predictive Learning in Medical Imaging
Fabian Drexel, Bernhard Kainz, Jakob N. Kather et al. (+4 more)
Joint-
embedding predictive architectures (JEPAs) learn by predicting teacher representations of masked regions from visible context. Point prediction summarizes the conditional target distribution and cannot reproduce variation that the context does not resolve. We call this constraint predictability bias. In computed
tomography (CT), recurrent anatomy is predictable from context, whereas the sporadic, localized pathology that determines clinical interpretation often is not. We introduce TAP-JEPA, a ViT-B/3D trained on 113,611 CT volumes that is competitive with state-of-the-art encoders (COLIPRI, Merlin, VoxelFM) in scan-level classification. We then audit the learned predictive pathway by replaying the exact masking, teacher, and predictor computations used during training. Prediction lowers the mean Skill (prevalence-normalized average precision) from 0.388 to 0.271 for pathology, but only from 0.921 to 0.873 for anatomy. Along the teacher direction, separating pathology from matched control regions in the same organ, prediction moves pathology 34.7% toward the controls and controls 13.6% toward pathology, with larger shifts farther from visible context. Replacing visible matched-control representations increases surrounding-target prediction loss more than fully replacing pathology representations across four pathology categories. Downstream, removing all final-layer pathology
tokens reduces the decision margin by at most 0.45% in four of seven scan-level probes. Together, these results show that contextual predictability is not a sufficient proxy for clinical relevance in medical representation learning. Training objectives should therefore retain diagnostic features regardless of their predictability from surrounding anatomy.
Read the full abstract ▾
All authors Fabian Drexel, Bernhard Kainz, Jakob N. Kather, Daniel Rueckert, Lisa C. Adams, Keno K. Bressem, Cosmin I. Bercea
Computation and Language
How Reliable are AMR Parser Outputs? Uncertainty Estimation for AMR Parsing
Anuj Kumar, Shintaro Ozaki, Yamuna Prasad et al. (+3 more)
Recent advances have significantly improved the performance of Abstract Meaning Representation (AMR) parsers, yet determining when their outputs can be trusted remains largely unexplored. This work presents the first study of uncertainty estimation for AMR parsers in a black-box setting using top-k beam-search candidates. Uncertainty is estimated from pairwise candidate similarities and evaluated using the Prediction Rejection Ratio. This work characterises the relationship between parsing performance and uncertainty, evaluates the reliability of beam candidate distributions, analyses the effect of evaluation metrics on uncertainty assessment, and identifies parsers that provide the strongest balance between performance and reliability. Experimental results show the value of uncertainty estimation as a complementary dimension for evaluating AMR parsers.
Read the full abstract ▾
All authors Anuj Kumar, Shintaro Ozaki, Yamuna Prasad, Katsuhiko Hayashi, Hidetaka Kamigaito, Taro Watanabe
Machine Learning
Learning Schwarzschild Geodesic Motion with Lagrangian Neural Networks
Sukru Caglar, Sena Kalabalik, Abdullah Umut Hamzaogullari et al. (+1 more)
Lagrangian Neural Networks (LNNs) learn dynamics from trajectory data by parameterizing a scalar Lagrangian and deriving accelerations through the Euler–Lagrange equation, providing a variational inductive bias that improves physical consistency over purely data-driven models. LNNs have recently been extended to general relativistic settings, leaving Schwarzschild geodesics as an open challenge. Training on complex relativistic systems is hindered by the diversity of the dynamics, as well as numerical instabilities and the difficulty of adequately sampling physically relevant, diverse orbital regimes. We introduce two coordinated improvements: a decoupled position–velocity normalization scheme that independently rescales each coordinate and its time derivatives, reweighting acceleration targets to balance contributions across all channels; and an energy-constrained log-uniformly sampled
dataset generation strategy informed by the innermost stable circular orbit (ISCO) structure. With these improvements, our model accurately reproduces perihelion precession and relativistic time dilation, conserves energy and angular momentum to within a few percent even after completing multiple orbits around the central mass and predicts orbital trajectories across eight orbital scenarios in close, medium, and far-field regimes. These results establish that LNNs, augmented with physically motivated normalization and sampling, can reliably learn geodesic dynamics in curved spacetime. Our work also represents the first successful training of LNNs on Schwarzschild geodesics and offers a promising direction for data-driven modeling of complex relativistic systems.
Read the full abstract ▾
All authors Sukru Caglar, Sena Kalabalik, Abdullah Umut Hamzaogullari, Arkadas Ozakin
Computer Vision
FPD-Drive: Future Policy Distillation for End-to-End Autonomous Driving
Li-Heng Chen, Qifeng Chen, Chengwei Wu et al. (+4 more)
End-to-end autonomous driving models are typically trained on real-world driving logs, which record only the trajectory actually executed in each scene. This provides limited supervision for learning alternative valid behaviors. Multi-target supervision can mitigate this limitation, but broader trajectory coverage makes safe candidate selection more challenging. We propose FPD-Drive, an end-to-end planner that distills privileged future knowledge into a visual driving policy to improve both multi-trajectory supervision and safety selection. Specifically, we introduce Future-Privileged Multi-Target
Distillation to transfer diverse, high-quality trajectory targets from a teacher with access to recorded future observations to the student. These targets extend supervision beyond the single recorded human trajectory. For candidate selection, we further introduce Safety-Aware Score Correction to correct ranking errors between nearby safe and unsafe candidates and raise underestimated safety scores of safe candidates. At deployment, the student requires neither future observations nor teacher inference. Our base model achieves 94.9 PDMS on NAVSIM v1 navtest and 55.9 EPDMS on NAVSIM v2 navhard. The scaled FPD-Drive-Pro improves these scores to 95.5 PDMS and 58.1 EPDMS, respectively, achieving SOTA performance among the compared methods on both
benchmarks. Zero-shot closed-loop evaluation on HUGSIM further yields an HD-Score of 45.1 and RC of 55.3.
Read the full abstract ▾
All authors Li-Heng Chen, Qifeng Chen, Chengwei Wu, Yingjie Zhang, Sheng Yang, Hongbo Fu, Shaoqing Ren
Numerical Analysis · Cross-listed from quant-ph
Block encoding of semiseparable matrices via their generators
Giacomo Antonioli, Gianna M. Del Corso and Roel Van Beeumen
We present an explicit
quantum circuit that constructs a block encoding of a generator-representable semiseparable (one-pair)
matrix directly from its two generators. For an $N\times N$ semiseparable
matrix with $N=2^{n}$, the
circuit uses $2n+2$ ancilla
qubits and has $O({\rm polylog} N)$ depth, and it realizes a $(2\sqrt{N},\,2n+2,\,2 \sqrt{2}\ \varepsilon)$-block encoding, where $\varepsilon$ is controlled by the accuracy of the state-preparation routines that load the generators. The building blocks of the
circuit are cyclic shifts, swaps, and Hadamard gates, each admitting an efficient implementation through the binary decomposition of the relevant indices.
Read the full abstract ▾
Cryptography and Security
Understanding and Mitigating Cross-Session Attacks via Persistent Artifacts in Agent Skill Composition
Dianshu Liao, Shidong Pan, Guangdong Bai et al. (+2 more)
Agent skills extend the capabilities of AI
agents by bundling instructions, code, and resources into reusable packages. During skill execution,
agents may produce or modify artifacts, such as files, configurations, and cached data, that are reused by other skills in later sessions. Since these artifacts can persist across sessions and later be accessed by other skills, they introduce a new attack surface that can be exploited to influence subsequent executions. However, the security risks arising from such cross-session skill interactions remain largely unexplored. In this work, we investigate cross-session composition attacks in skill-based AI
agents and develop a runtime defense against them. Specifically, we characterize three attack mechanisms, namely Instruction Propagation (IP), Data Boundary Violation (DBV), and Evidence Poisoning (EP), through which malicious effects propagate across skill executions via persistent artifacts. To evaluate whether existing
agents can resist these attacks while completing legitimate tasks, we construct SkillRelayBench, a
benchmark of 270
adversarial cases drawn from 30 cross-session skill-composition scenarios across ten domains. Our evaluation of seven models across Codex CLI, Gemini CLI, and Claude Code reveals attack success rates (ASR) ranging from 46.7% to 77.4% and attack chain success rates (ACSR) ranging from 35.6% to 61.1%. Successful attack chains cover all five target security consequence categories, highlighting the broad impact of these attacks. To mitigate these risks, we propose SkillRelayGuard, which restores artifact provenance context and provides pre-execution advisory review while leaving the final execution decision to the
agent. Evaluation across three
agent settings shows that SkillRelayGuard reduces overall ASR from 69.5% to 10.9% and ACSR from 54.8% to 10.0%, while increasing legitimate task completion from 79.6% to 87.5%.
Read the full abstract ▾
All authors Dianshu Liao, Shidong Pan, Guangdong Bai, Zhenchang Xing, Xiaoyu Sun