Papers

More than 300 million people worldwide are affected by one of over 7,000 known rare diseases, yet diagnosis remains difficult because patients initially present with incomplete and heterogeneous phenotypes. We present HPOQuest, a training-free framework for sequential phenotype acquisition in rare-disease diagnosis. Starting from a small set of observed patient phenotypes, HPOQuest maintains a probabilistic disease ranking and iteratively selects informative follow-up questions to support clinicians during patient assessment. Confirmed phenotypes update the disease ranking, while all responses update the candidate question set. Across four benchmark cohorts, HPOQuest substantially improves diagnosis from sparse initial phenotypes, with gains of up to 30% points at Recall@1 and 45% points at Recall@5. These results demonstrate that sequential phenotype acquisition can substantially improve rare-disease diagnosis from limited initial clinical evidence.

Modeling physical dynamics, including how objects move, interact, and change state, is central to video world models for embodied AI. We present StrucPhysVideo, a family of video world models that bridges physics-focused data curation with language- and action-conditioned prediction of scene evolution. Our data pipeline combines motion-aware video segmentation, quality and content filtering, and physical relevance verification with structured annotations of objects, materials, and temporally localized interactions. By disentangling camera motion from object behavior and explicitly describing contact, deformation, and state transitions, the pipeline provides supervision grounded in observable physical events. Building on these data, we introduce StrucPhysVideo-TI2V, a sparse Mixture-of-Experts (MoE) text-image-to-video model trained with a curriculum that progressively emphasizes physical dynamics while retaining general-domain video data. StrucPhysVideo-TI2V achieves state-of-the-art performance on Physics-IQ Verified, scoring 45.5% and outperforming Cosmos3-Super-Image2Video by 2.8 percentage points. Caption ablations across backbones further demonstrate the effectiveness of physics-focused supervision. We further extend StrucPhysVideo-TI2V to StrucPhysVideo-IA2V, an interactive image-action-to-video world model that predicts visual outcomes from robot end-effector commands. Action conditioning, causal autoregressive generation, and few-step distillation enable incremental robot rollouts with only four denoising steps. Together, StrucPhysVideo advances physical dynamics modeling from image- and language-conditioned video prediction toward action-driven interaction.

Latent neural operators improve the efficiency of operator learning for partial differential equations (PDEs) by performing the main computation on compact latent representations. However, directly compressing the input representation to obtain such compact representations may discard solution-relevant spatial information, especially for PDE solutions with multiscale structures. To address this problem, we propose HiLNO, a hierarchical latent neural operator that constructs a fine-to-coarse-to-fine latent space and further introduces multi-scale supervision (MSS) and anisotropic Gaussian attention. The hierarchy mitigates potential information loss during compression, while MSS aligns intermediate predictions with downsampled target fields, encouraging solution-relevant structures to be captured across multiple spatial scales. Anisotropic Gaussian attention enables feature transfer across the hierarchy, making HiLNO applicable to general geometries. Experiments on representative PDE benchmarks and a large-scale automotive aerodynamics task show that HiLNO achieves competitive predictive accuracy, while reducing the parameter count by an average of 84.4% and FLOPs by an average of 69.2% compared with LinearNO. Additional experiments demonstrate effective generalization to unseen spatial resolutions. Code is available at https://github.com/JcLimath/HiLNO.

Multi-turn agent trajectories often contain redundant rounds (failed tool calls, parallel sub-queries, verification-only steps) that inflate both training and inference cost. We propose viewing each trajectory as a round-level dependency DAG that exposes which rounds are globally load-bearing for the final answer, and fine-tune agents on trajectories refined through this DAG. Given an LLM-annotated DAG, these edits are deterministic and interpretable, with optional rephrasing. Models trained on these refined trajectories consistently outperform those trained on the original trajectories at lower inference cost. Specifically, across four multi-modal QA benchmarks, our refinements improve downstream accuracy by up to $1.7$\,pp over vanilla SFT (and $5.7$\,pp over an LLM-deletion baseline) while reducing per-sample inference messages by up to approximately $40\%$ and inference tokens by up to approximately $48\%$, translating to substantial savings in compute and serving cost. Code is available.

Stochastic subspace methods have gained popularity as gradient descent based techniques for large scale optimisation problems, especially in distributed settings. In this paper, we introduce the technique of "persistence of memory" to greatly extend and improve the random subspace methods. To this end, we leverage a vector that is only weakly correlated with the gradient in order to provide a guiding structure to the generative process of the random subspace along which the descent is going to take place. This guidance vector may be fixed for a large number of iterations, only to be refreshed at wide intervals (on whose size we can provide guarantees in terms of problem parameters). In important machine learning settings, such as optimisation problems embodying sparsity or a minibatch structure, we show that the guidance vector can be obtained in an effective and computationally inexpensive manner by leveraging the structured properties of the problem. En route, we establish to our knowledge the first theoretical analysis of classical SSD methods for sparse functions. In a local neighbourhood of the optimum, we demonstrate an alignment phenomenon of our gradient estimates with a low-lying eigenvector of the Hessian, allowing a once-for-all computation of the guidance vector which renders the method computationally favourable even in scenarios with unstructured objectives.

What is a gait? Appearance-based gait networks consider a gait as the human shape and motion information from images. Model-based gait networks treat a gait as the human inherent structure from points. However, the considerations remain vague for humans to comprehend truly. In this work, we introduce a novel paradigm Vocabulary-Guided Gait Recognition, dubbed Gait-World, which attempts to explore gait concepts through human vocabularies with Vision-Language Models (VLMs). Although VLMs have achieved the remarkable progress in various vision tasks, the cognitive capability regarding gait modalities remains limited. The success element in Gait-World is the proper vocabulary prompt where this paradigm carefully selects gait cycle actions as Vocabulary Base, bridging the gait and vocabulary feature spaces and further promoting human understanding for the gait. How to extract gait features? Although previous gait networks have made significant progress, learning solely from gait modalities on limited gait databases makes it difficult to learn universal gait features for practicality. Therefore, we propose the first Gait-World model, dubbed {\alpha}-Gait, which guides the gait network learning with vocabulary knowledge from VLMs. However, due to the heterogeneity of the modalities, directly integrating vocabulary and gait features is highly challenging as they reside in different embedding spaces. To address the issues, {\alpha}-Gait designs Vocabulary Relation Mapper and Gait Fine grained Detector to map and establish vocabulary relations in the gait space for detecting corresponding gait features. Extensive experiments on CASIA-B, CCPG, SUSTech1K, Gait3D and GREW reveal the potential value and research directions of vocabulary information from VLMs in the gait field.

Agentic browsers can execute security-sensitive actions under a user's authenticated session, making indirect prompt injection and deceptive confirmation interfaces a direct threat to action integrity. Existing human-in-the-loop (HITL) safeguards are insufficient when the approval prompt itself can be influenced by untrusted page content or model-generated text. We present the Verifiable Action Card (VAC), an architectural defence that reconstructs approval information from the ground-truth pending browser action and trusted intent provenance, renders it out-of-band in the trusted browser chrome, and binds approval to the exact action re-verified at dispatch. VAC combines provenance fencing, a ground-truth action descriptor, default-deny confirmation, provenance-aware risk gating, and execution binding. We implement VAC in a complete agentic browser and evaluate it on a 24-scenario benchmark covering confused-deputy attacks, Lies-in-the-Loop dialog forging, indirect prompt injection, adaptive action substitution, provenance evasion, and legitimate tasks. Across the evaluated LLMs, attack success without VAC ranges from $68\%$ to $100\%$, whereas VAC reduces attack success to $0\%$ on every model, with $78\%$ legitimate-task completion and a $0\%$ false-block rate. These results show that grounding approval in the action that will actually execute provides architectural protection against security failures that prompt-level defences and conventional HITL confirmation cannot reliably prevent.

Weekly influenza surveillance counts guide vaccine distribution and public-health alerts, yet they are hard to forecast. Each region offers only a few seasons, waves shift in timing and height every year, and information that helps while a wave grows misleads after its peak, whereas last season's shape stays informative for a year. Existing epidemic graph models and general forecasters read a short fixed window and treat all past information alike, so they neither exploit earlier seasons nor discard stale associations when the epidemic phase changes. To address these limitations, we propose TERN, a forecaster built around a delta-rule fast-weight memory that decays channel-wise and erases along a learned address under gates driven by local epidemic-phase features, combined with an explicit seasonal reference and online adaptation. On three Cola-GNN influenza benchmarks, TERN outperformed epidemic graph models and general forecasters, matched or exceeded seasonal references, and a controlled comparison confirmed the contribution of the memory itself.

Recovering 3D human body motion from video is important for applications such as rehabilitation assessment and sports performance evaluation. For prosthesis users, this requires capturing both natural body joints and the geometry of the prosthetic device, a challenge that existing methods are not designed to address. Model-based estimators rely on body models trained on non-amputee individuals and cannot represent prosthesis geometry, while model-free methods lack body kinematic priors and are unreliable under occlusion. This challenge is particularly prominent for users of running-specific prostheses (RSPs), where the RSP has a complex curved geometry and moves dynamically during exercise. To fill this gap, we collect RSP3D, the first 3D dataset of RSP users, covering essential daily-life and exercise actions from participants with varied amputation conditions, using a multi-camera marker-based motion capture setup. We formally define the task of prosthesis-aware 3D pose estimation, evaluate representative methods in a zero-shot setting, and confirm their individual limitations. We further propose a hybrid baseline combining model-based body joint estimation with model-free RSP shape recovery, establishing a starting point for future research.

Multimodal Aspect-Based Sentiment Analysis (MABSA) infers fine-grained sentiment polarity toward specific aspects by jointly modeling text and images. Despite progress in cross-modal fusion, two challenges remain in multi-aspect settings: (1) multimodal noise, where aspect-irrelevant content distracts sentiment learning; and (2) weak cross-modal sentiment alignment, as visual evidence can be ambiguous and textual–visual sentiments may conflict, limiting multimodal complementarity. To address these issues, we propose a Gated Noise-filtered Sentiment-Relevance Interaction (GNSRI) framework. It employs a gated noise-filtering module to suppress sentiment-irrelevant features and enhance aspect-aware sentiment cues, and a sentiment-relevance interaction module to capture consistent and conflicting cross-modal signals at micro and macro levels. Finally, a learnable decision fusion mechanism adaptively combines predictions from textual, visual, and cross-modal branches at the aspect level. Experiments on public MABSA benchmarks show that GNSRI outperforms state-of-the-art methods, improving accuracy by 1.94% and 2.06% on Twitter-2015 and Twitter-2017, respectively.

Phase-field trajectories governed by the Allen–Cahn equation determine the effective force $G=F'/\eps^2$, but not the free-energy potential $F$ and interfacial scale $\eps$ separately. We introduce surface-tension-calibrated Allen–Cahn identification (STAC), a two-step method that resolves this ambiguity using an independently supplied surface tension. First, space–time weak moments produce a linear inverse problem without differentiating the measured field. A Bernstein representation with positive coefficients enforces two stable pure phases and a single central energy maximum. Second, the surface tension fixes the remaining scale algebraically. We prove scale equivalence of the forward model, uniqueness of the calibrated pair within this class, and finite perturbation bounds that remain valid when the potential vanishes at the pure phases. Experiments with resolved synthetic phase fields separate the effects of the structural constraint, ridge regularization, and constitutive approximation error. Across 80 shared noisy records, unconstrained degree-five regression produces six potentials with an incorrect well structure. Positivity combined with ridge regularization eliminates these violations and reduces the mean force error from 8.70% to 5.66%. Lower-degree models are nevertheless more accurate in some tests, and an admissible law outside the positive Bernstein family shows how the constraint can introduce approximation bias. STAC thus recovers a structurally admissible, physically scaled potential while making explicit which information comes from the observed dynamics and which comes from the independent surface-tension datum.

Identifying isolated points is important in image processing applications such as medical imaging, astronomy and quality control management. Other domains, such as cybersecurity, also present challenges that can be framed as image processing problems. One example of particular interest is the identification of anomalous single nodes in spatially organised networks where groups of nodes in different regions share similar feature values. This task can involve both binary and more complex grayscale images. However, existing methods face limitations: template matching is infeasible for grayscale images, while 2nd order derivative based methods are highly sensitive to noise and require user-specified thresholds. To overcome these issues, a novel method is proposed for detecting meaningful single-pixel deviations in images. This approach modifies and extends a neuron model, originally designed for anomaly detection, to operate on spatially diameter limited receptive fields that incorporate excitatory and inhibitory regions. The result is a method that is free from user-specified thresholds and parameters, and can be applied to both binary and grayscale images, providing an effective, robust and efficient solution.

In this paper we study the genome rearrangements done by translocation events. Genome rearrangements were used to measure evolutionary distance between organisms since 1936 (Dobzhansky and Sturtevant). The chromosomes are represented as strings of DNA and the translocation operation is defined as the exchange of prefixes between two strings. This operation results in the creation of two new strings (chromosomes) that can then be utilized in subsequent translocations. A translocation is referred to as contiguous if the new strings are produced in a single copy, so each of them can be used in only one subsequent operation. When the words produced by a translocation operation are considered to have an infinite number of copies, the translocation is referred to as non-contiguous. If the exchanged prefixes are of equal length, the translocation is called uniform. Otherwise, the translocation is termed non-uniform. The translocation distance between two sets of strings, termed the input set and the target set, represents the minimum number of translocations necessary to obtain all the strings in the target set via translocation operations. We prove that both the non-uniform contiguous and the non-uniform non-contiguous translocation distance problems are NP-hard over arbitrary finite alphabets, where the alphabet is part of the input. For the case in which the target set consists of a single string, we give a fixed-parameter tractable algorithm parameterized by the length of the target string.

Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in cyber-physical systems. However, when sensors fail, learning-based predictors can produce physically implausible estimates that propagate to system-level failures. We argue that real-world deployment demands robustness and introduce MuViS-C, the first multi-domain benchmark of robustness against common sensor failures in learning-based virtual sensing. Building on an existing nominal-performance benchmark and established corruption taxonomies, it covers ten sensor failure modes, from subtle drifts to catastrophic signal dropouts, at multiple severities. These are paired with complementary robustness measures capturing average error under corruption, relative degradation, and worst-case fragility. Across nine datasets from six domains, we benchmark six architectures spanning gradient-boosted trees and the major inductive biases for sequence modeling: convolution, recurrence, attention, and MLP-mixing. On the attention-based architecture, we further probe three robustification strategies. We find that (i) every model degrades substantially under corruption, becoming worse than a naïve predictor on at least one corruption setting, (ii) gradient-boosted tree ensembles achieve strong robustness, and (iii) dedicated robustification closes the gap between the attention-based architecture and the most robust models, though each strategy hurts nominal performance. The benchmark's multi-domain design proves essential, as model rankings shift across datasets, and no single domain captures the full robustness picture. MuViS-C is open-source and extensible to new datasets, failure modes, measures, and models.

Policies for robotic manipulation are produced by training on large teleoperated datasets. These datasets typically consist of free-space trajectories, making them difficult to transfer to test-time environments with obstacles. Previous methods for closing this gap have largely fallen into two groups. Dataset augmentation addresses it at training time but needs obstacle geometry in advance, whereas steering an existing checkpoint at inference time avoids that requirement but is limited in flexibility. Our method draws from both areas without inheriting either drawback. DetAug applies an obstacle-blind augmentation scheme to the transit phases of a free-space dataset, leaving object interactions untouched, and records the augmentation parameters as an explicit conditioning label. At inference it samples a batch of labels and executes the trajectory with the lowest collision cost. On the SafeLIBERO benchmark DetAug achieves a collision-free success rate more than 20pp above the next best method, and selecting over the label space outperforms guidance on the same policy by 26pp. On real hardware, inference-time steering methods collapse on tasks requiring large detours, while DetAug matches or exceeds an obstacle-conditioned baseline without ever seeing obstacles in training.

We report the results of a Turing Test conducted in Finland in the Finnish language. Because languages and cultural contexts are unevenly represented in LLM training data, we expected the model (ChatGPT 5.2) to perform worse in a Finnish-language Turing Test than in previously studied English-language US contexts. We also present model-generated role prompting as a replicable technique for conducting comparative LLM-based Turing Tests designed to improve construct validity. Contrary to our expectations, the LLM passed the Finnish Turing Test. A prominent source of error was participants' reliance on linguistic cues, particularly colloquial Finnish, as markers of human authorship. We reframe the Turing Test from a test of intelligence to a comparative method for examining whether an AI system can display credible membership in a particular social world. Because its outcome reflects model capabilities, prompted identity, insider competence among human participants, and their AI literacy, the method provides a useful probe of the human-machine boundary across domains.

Conditioning a video generator on multiple images requires preserving appearance while associating each reference with its intended role. We present MSR (Multiple Subject Reference), a slot-aware conditioning scheme for LTX-based video generation. Each reference image is independently encoded as a static clip and represented by a separate latent-token group. A compact Fourier-feature multilayer perceptron adds a numeric slot embedding, while slot-dependent temporal offsets modify the group's rotary coordinates. The reference groups are prepended to noisy target tokens and serve as clean context during target-only flow-matching training. We implement this scheme through low-rank adaptation and release the resulting weights and inference workflows. Qualitative examples demonstrate compositions containing distinct characters and referenced environments in realistic and stylized scenes. Development observations suggest reduced reference confusion relative to an earlier continuous-reference baseline, while similar clothing, complex garments, and viewpoint changes remain challenging. We describe the conditioning mechanism, the retained training configuration, and the observed strengths and limitations of the released system. A supplementary audio-reference experiment adds voice conditioning while keeping the visual parameters frozen.

Vision-language-action models (VLAs) have trans- formed the field of robotic manipulation in recent years by combining the semantic understanding of LLMs with the precise control of flow-matching policies. Advantage conditioning is a recent technique that iteratively improves VLAs by training a value function on deployment data and using this to train an advantage-conditioned policy. Previous works have only applied simple, low-information success/failure rewards, which leave the value function unable to distinguish states of differing quality beyond how far along the task they appear. Motivated by an exploration of out-of-distribution (OOD) detection methods, we introduce Distance-based Advantage Learning (DistAL), which, by using an embedding space distance as a reward, produces a more informative value function and subsequently a higher downstream task success rate. We validate our method on a series of simulation benchmarks and dexterous bi-manual manipulation tasks on real hardware.

Software supply-chain security requires accurate identification of third-party components and an understanding of how they evolve from development to execution. Existing software composition analysis (SCA) approaches examine manifests, build environments, release artifacts, containers, or runtime states, but typically produce only stage-specific views of software composition. As dependencies are resolved, removed, repackaged, and transformed across lifecycle stages, a single snapshot cannot capture both where a component originates and where it ultimately ends up. Combining snapshots from multiple stages still leaves their cross-stage relationships unresolved. We present SCA-Agent, an agent-based approach to lifecycle-aware SCA that reconstructs evidence-backed component lifecycle traces across Code, Build, Release, Deploy, and Runtime. SCA-Agent adaptively explores project-specific analysis paths, gathers stage-specific evidence, and correlates observations across stages to recover component identities, versions, introduction paths, propagation relationships, and final lifecycle states. We evaluate SCA-Agent on 105 real-world projects from the Java, JavaScript, and Python ecosystems. SCA-Agent achieves the highest component detection F1 across all lifecycle stages and ecosystems. For vulnerability exposure assessment, it reaches an F1 score of 96.69%, exceeding the best traditional SCA tool by 18.76 percentage points. These results show that lifecycle-aware SCA supports traceable component provenance and more accurate software supply-chain risk assessment.

AI-powered medical scribes are increasingly used to transcribe doctor-patient conversations and automate clinical documentation. However, large-scale real-world consultation datasets are scarce due to the sensitivity of clinical conversations, leading developers to rely on simulated and LLM-generated synthetic consultations. While scalable, these alternatives may fail to capture culturally situated patterns of clinical interaction. We introduce interactional cultural markers, measurable patterns of doctor-patient interaction grounded in cross-cultural clinical communication, and use them to compare real, simulated, and synthetic consultations from Indian and US clinical contexts. We find distinct patterns of participation and control: Indian consultations involve greater patient participation but stronger doctor control, while US consultations exhibit balanced participation and open-ended discussion. Synthetic Indian consultations often fail to reproduce these patterns, instead converging toward US-like interaction. We identify additional synthetic signatures, including excessive doctor explanation and formulaic patient responses. We conclude by discussing implications for generating culturally grounded synthetic clinical conversations.

Large language models are increasingly trained on GPUs distributed across multiple regions, but geo-distributed training is challenging in practice. Real clusters often contain GPUs with different speeds and memory capacities, and they communicate over slow wide-area networks. Our analysis shows that this creates serious problems: existing synchronous methods preserve stable updates, but fast GPUs wait up to 20.9% of their runtime for slower ones, and all workers spend, on average, 65.8% of their runtime on synchronization. Recent asynchronous methods reduce waiting time but worsen the model accuracy due to stale updates. To address the problems, we present GeoMesh, a synchronous geo-distributed training framework for heterogeneous GPUs. GeoMesh balances per-worker workloads by assigning each GPU a suitable batch size and number of inner steps, so faster GPUs do more useful work instead of waiting. It also reduces communication volume by nearly 32x by exchanging compressed sign-based pseudo-gradients with lightweight magnitude and token count. Across heterogeneous GPUs and Azure-derived WAN, GeoMesh reduces time-to-target perplexity by up to 70.2% over representative baselines and lowers straggler- and WAN-induced GPU idle by up to 8.0x and 5.6x, respectively, while preserving comparable zero-shot accuracy.

Emotions are an essential aspect of human communication, particularly on social media, where authors frequently combine text and images to convey their emotions. Yet prior work on emotion analysis of social media posts has overlooked two important aspects in regard to measuring how well readers can reconstruct the authors' intent: (1)~the image modality, with most work focusing solely on text, and (2)~the real-world events that trigger the expressed emotions, and their relationship to the post content. We therefore study the relation between (a) the author's experience of the event that caused them to write a social media post and (b) the content of the post, with a focus on readers' capability to reconstruct that emotion expression. To do that, we introduce the Multimodal Multi-Emotion-Model dataset Mult2EMo, created by collecting annotations from both authors and readers on the posts and their triggering events. We find that reconstruction is possible but challenging for both human readers and computational models. We show that understanding the triggering event is crucial for accurate reconstruction, and that reconstruction is particularly challenging when posts rely heavily on the image to express emotion.

We present a robust benchmark for measuring cultural value orientation in large language models on the two Inglehart-Welzel axes over several domains and roles (hence GYROval - Gridded Yielding of Robust value Orientation), together with the results of administering it to twenty models. Items are binary contrastive scenarios in the sense introduced by CDEval: both options are legitimate courses of action, neither is correct, there is no answer key, and a model's score on an axis is the proportion of its responses falling on the counted pole. Eleven of the twenty models were additionally administered a paired Russian translation of the identical items and a second sampling temperature. The instrument is publicly released in both languages. Stability was assessed by treating the vignette as the unit of analysis, ranking the models within the levels of each perturbation factor, and summarising the agreement between levels by tie-corrected Kendall's W against an empirical permutation null.

We introduce a new finite element discretization for a mixed formulation of the two-dimensional incompressible Stokes equations with symmetric viscous stresses. The method is based on a mass-conserving stress-yielding formulation (Gopalakrishnan, Lederer, Schöberl; A mass conserving mixed stress formulation for the Stokes equations; IMA J. Numer. Anal., Vol 40, 2020) with symmetric stresses, with the key novelty that the symmetry of the stress tensor is enforced exactly as an intrinsic property of the discrete space. This space is constructed on the Clough–Tocher macroelement split and consists of matrix-valued functions whose normal-tangential components across macroelement interfaces are continuous. Since the exact symmetry is enforced via local polynomial bubble functions on the subelements, which can be eliminated via static condensation, the number of globally coupled degrees of freedom coincide with those of the original mass-conserving stress-yielding formulation. The resulting pressure-robust method is stable without requiring any additional enrichment. We establish optimal convergence rates for all the variables and present numerical experiments that confirm the theoretical results.

Despite their high accuracy on point-wise metrics, machine learning weather forecasting models can exhibit different failure modes such as blurring, periodic irregularities, and other unphysical spatial artifacts. This has motivated a variety of metrics to detect known failure cases. Existing metrics fix a representation or transformation in advance, and that choice limits the artifacts they can detect. We propose to train a discriminator for separating reference data from the model's output, and using its output logit to obtain a divergence-like realism score. The discriminator learns whatever separates the model's fields from real weather, adapting to whichever failure mode that model exhibits. We compare our learned atmospheric critic to existing metrics using various synthetic corruptions applied to ERA5 reanalysis data. Our method successfully identifies the corruptions and ranks their severity, while existing metrics fail on at least one corruption. Additionally, we evaluate forecasts from real weather models, and find that the realism score degrades with longer lead times and the metric generally assigns higher realism to numerical models than to machine learning models.

Square jigsaw reassembly requires recovering the spatial arrangement of shuffled fragments from their visual content and pairwise relationships. While recent studies have made substantial progress, existing benchmarks typically assume that all fragments are provided upright, reducing reassembly to a permutation problem. We study the generalized problem in which each fragment may also have gone through an unknown rotation. For this setting we establish a gauge-unobservability theorem: the minimum of the weighted least-squares objective is exactly invariant under a uniform global rotation of arbitrary magnitude, so no residual-based criterion can recover the global orientation. The theorem further identifies how the issue of global orientation can be resolved: an orientation anchor estimated from the content of a single fragment, lying outside its scope, suffices. To address the above, we propose JigSync, which attains 63.8% and 31.8% absolute accuracy (AA) on GAP-3 and GAP-5, respectively, the highest reported on both, while additionally recovering a rotation per piece that neither benchmark requires. We release JigSync, a degradation protocol that sweeps shape, erosion, photometry, grid size, and rotation independently.

Vision-Language-Action (VLA) policies commonly run Vision-Language Model (VLM) backbones with billions of parameters at every policy inference, which costs latency and energy. We revisit a decoupled alternative for multi-task manipulation: separate vision and language encoders whose representations condition a compact action head. We run a standardized comparison that varies the vision encoder, the language encoder, and the action head while holding the demonstrations, the training-step budget, the tasks, the evaluation protocol, and the measurement platform fixed, against seven VLA baselines. The resulting Decoupled Embodiment Model (DEM) combines a fine-tuned DINOv3 vision encoder, a frozen NeoBERT language encoder, and a MeanFlow head that generates an action chunk in one forward pass. On 18 RoboCasa tasks evaluated with held-out instruction paraphrases and randomized scenes, DEM reaches 55.6% mean success against 56.9% for GR00T N1.7 and 54.6% for $\pi_{0.5}$, and on three real-robot tasks it reaches 66.0% against 68.0% for GR00T N1.7. On the same workstation, DEM needs 6.1\,ms per policy forward pass, a maximum throughput of 162.7 policy calls per second, and draws an estimated 2.07\,J of GPU energy per call, eight to seventeen times the throughput and six to fifteen times less energy than these VLM-backbone policies. Within this trained-task regime, DEM sits on the observed success–latency–energy frontier and provides a strong, efficient baseline for language-conditioned robot skills.

Classical CSI feedback in FDD massive MIMO transmits a compressed reconstruction of the channel, optimizing fidelity to the original signal regardless of the downstream task. We propose a semantic communication perspective: instead of reconstructing the channel, the UE transmits a learned semantic embedding optimized end-to-end for beam selection at the gNB. Comparing reconstruction-oriented feedback (CsiNet) against task-aware semantic feedback across two input domains and three observation scenarios, we show that a semantic embedding of just $d=8$ real values from only 43 NR CSI-RS pilots in the angular-delay domain achieves the highest beam prediction accuracy, outperforming every method with access to the full 512-subcarrier channel. The key insight is that beam-relevant information is intrinsically low-dimensional: the semantic encoder learns to discard reconstruction-irrelevant structure and retain only a compact representation that is relevant to beam selection, realizing the core principle of semantic communication: transmit the intent, not the signal.

Reliable agent evaluation is complicated by automatic harness optimization, which repeatedly uses a released benchmark $B_{\mathrm{rel}}$ to guide a Proposer that edits prompts, memory, retrieval, tools, and control code around a fixed foundation model. Task holdout is commonly used to guard against harness overfitting. It varies semantic tasks but leaves the benchmark protocol fixed, so a bad genius Proposer can produce a cheating harness whose improvement over the initial harness on $B_{\mathrm{rel}}$ depends on a benchmark-wide shortcut. We introduce Counterfactual Harness Search and Evolution (CHASE), which casts harness evolution as constraint generation over valid counterfactual benchmarks. After each Proposer update, a Challenger searches for an executable protocol transformation with large gain destruction. A validity firewall checks that task semantics are preserved, while a held-out confirmation set determines whether the counterfactual enters a finite archive. We formalize an ideal shortcut-neutralized benchmark $B_0$ and establish theoretical guarantees linking finite counterfactual archives to $B_0$ and characterizing sequential Challenger search. We evaluate CHASE on Syn-Ledger and OfficeQA, where CHASE retains strong released-benchmark gains while substantially reducing gain destruction under valid protocol transformations.

Online multi camera 3D tracking must maintain scene global identities across synchronized views, yet query-based trackers carry these identities only implicitly in the instance bank, where they fragment upon query interruption. We present an online architecture that recovers association accuracy by predicting IDs explicitly over recurrent sparse queries. An outside-in Sparse4D detector fuses calibrated views into world frame 3D detections while propagating a sparse query bank, and a causal MOTIP ID decoder associates detections against a finite trajectory memory. We adapt MOTIP's relative-ID prediction and recycled slot runtime to globally fused 3D observations, and introduce metric spatial gating and proximity based newborn recovery. On the official 2026 AI City Challenge Track 1 test set, our method raises HOTA from 29.63 with native instance bank identities to 38.01, primarily through an AssA increase from 20.83 to 31.10, and ranks third on the public leaderboard. Full-sequence validation over all 9,000 frames of each scene shows that decoupled ID training improves HOTA over native identities, whereas continuing detector training alongside the detached ID objective produces scene-dependent gains and losses.