Computer Vision
Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model
R. James Cotton, J.D. Peiffer, Lucinda Williamson et al. (+2 more)
State-of-the-art
monocular body recovery methods predict mesh vertices and angles on the corresponding kinematic tree, but their outputs lack biomechanically defined joint angles that downstream applications like clinical and biomechanical analyses require. We extend an existing foundation model, SAM-3D-Body, with an additional biomechanical prediction head that, from a single RGB image, regresses the joint angles and scales of a biomechanical model. Training this model presents a challenge, as there are limited
datasets of paired images and biomechanical fits. To overcome this, we supervise biomechanical outputs with in-loop optimized targets from a Levenberg-Marquardt solver performing inverse kinematics fits against markers from the mesh predictions. This allows distilling the biomechanical head from the mesh head, even from unlabeled images. To make this work with GPU-optimized biomechanical models in MuJoCo, the entire model was implemented in JAX using Equinox. We trained this distilled output head on the publicly released SAM-3D-Body
dataset. We then validated this model on biomechanical fits to two publicly available marker-based
datasets, MoVi and BioCV, as well as movements from a clinical cohort captured with multiview markerless motion capture. The resulting model outperforms existing models for direct regression of biomechanics from images while only slightly underperforming the state-of-the-art
monocular biomechanics method that performs more costly inference-time optimization of entire trajectories.
Read the full abstract ▾
All authors R. James Cotton, J.D. Peiffer, Lucinda Williamson, John Leske, Georgios Pavlakos
Computer Vision
Everybody Tracking Every Body
Daeyun Shin, Yunhan Zhao, Shu Kong et al. (+2 more)
We address the problem of 3D body pose estimation of multiple interacting people from their
egocentric views with centralized coordination. Each individual wears a camera recording
egocentric video and IMU data. Processing this
video with VIO SLAM provides high-quality tracking of each
egocentric camera through space. The first-person view from one individual provides third-person observations of other people, although these exocentric observations are sparse, intermittent, and of highly variable reliability as both cameras and subjects move. To integrate these synchronized data streams, we propose a
diffusion-based approach that fuses estimates of pose based on head motion derived from
egocentric camera motion with exocentric pose observations, conditioning on both observation content and reliability. Our model is trained on a mixture of single-person motion-capture data and multi-person
video in order to learn rich priors for body motion trajectories and
video observation reliability. Evaluation on challenging multi-person
datasets suggests our fusion approach improves over motion-only and
vision-only baselines in terms of both absolute and relative pose accuracy.
Read the full abstract ▾
All authors Daeyun Shin, Yunhan Zhao, Shu Kong, Alexander C. Berg, Charless Fowlkes
Computer Vision
Dior: Drawing the Light of Image via Material-Decoupled Illumination Representation
Xuanpu Zhang, Xuesong Niu, Haoxiang Cao et al. (+4 more)
Controllable image relighting is an important problem in image editing, and hand-drawn scribbles provide an intuitive interface for specifying the desired illumination. However, existing methods do not establish a consistent and effective mapping between scribble inputs and relighting results, limiting their ability to control illumination intensity, chromaticity, and complex spatial distributions. We address this limitation by introducing a material-decoupled illumination representation, termed the Lumi Map, which establishes an explicit mapping between user scribbles and the resulting illumination, thereby improving both relighting accuracy and controllability. Specifically, we use a renderer to synthesize source image-Lumi Map-relit image triplets and train the model to predict the target relighting result conditioned on the Lumi Map. To mitigate the domain gap introduced by synthetic data, we further perform reconstruction training on real relighting pairs, improving the model's generalization to real-world images. Finally, we present Dior-Light, an image relighting method controlled by hand-drawn strokes. Extensive experiments demonstrate that our method outperforms existing approaches in relighting accuracy and enables effective control over illumination intensity and chromaticity on in-the-wild images.
Read the full abstract ▾
All authors Xuanpu Zhang, Xuesong Niu, Haoxiang Cao, Ruidong Chen, Jianhao Zeng, Changqian Yu, Shiguang Liu
Computer Vision
Hallucination Mitigation for Large Vision-Language Models via Implicit Feature Stabilization
Aditi Sarker, Rafi Ibn Sultan, Hui Zhu et al. (+2 more)
Large
Vision-
Language Models (LVLMs) are prone to
hallucinations: they fluently describe objects, attributes, and scenes that are not in the image. We connect part of this failure to a measurable property of their representations, feature instability, where mild semantics-preserving perturbations of the input cause large changes in the learned
embeddings;
hallucination rates rise together with this variability. Existing stability-motivated remedies are explicit, in the sense that they intervene at inference time through latent steering or constrained decoding, and pay for it on every query. We propose implicit stabilization instead: perturbation-invariance is built into the model weights during fine-tuning, and nothing extra runs at deployment. Our framework, INFUSE, first stabilizes visual and textual representations around perturbation-averaged and ground-truth anchors, then aligns the stabilized representations across modalities with bidirectional contrastive objectives. We prove that the anchor's root-mean-square deviation from the perturbation-mean representation shrinks at rate $1/\sqrt{K}$ in the number of views, and that under a Lipschitz decoder, this bounds how much any perturbation can change the model's
hallucination behavior. On LLaVA-1.5, LLaVA-1.6, and Qwen3-VL-8B-Instruct, INFUSE reduces AMBER CHAIR by 46-63% relative to each base model, improves ObjHal, MMHal, HallusionBench, and POPE, and preserves VQA-v2 and TextVQA, all with no inference-time overhead.
Read the full abstract ▾
All authors Aditi Sarker, Rafi Ibn Sultan, Hui Zhu, Dongxiao Zhu, Prashant Khanduri
Computer Vision
Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentation
Chandler Timm C. Doloriel, Yunbei Zhang, Sarthak Kumar Maharana et al. (+5 more)
Open-vocabulary semantic
segmentation (OVSS) relies on
vision-
language alignment to recognize arbitrary text-defined categories, yet this
alignment is fragile under continual test-time distribution shift. Our diagnostic analysis reveals that
entropy minimization drives patch-level class collapse, continual updates erode
vision-
language alignment, and redundant gradients from low-shift samples waste computation. We propose Diversify, Anchor, and Filter (DAF), a stabilization framework that augments
entropy-based adaptation with a marginal diversity loss that resists collapse, a cross-modal anchor consistency loss that constrains feature drift relative to a frozen source model, and feature salience filtering that skips low-value backward passes to offset part of the source-anchor overhead. We evaluate on five
datasets spanning natural scenes, autonomous driving,
underwater imagery, and remote sensing with their corrupted variants. Across the evaluated continual shifts, DAF remains stable where
entropy minimization collapses, improving mIoU by over 8 points on Pascal VOC20-C, over 9 points on LoveDA, and over 3 points on Foggy Cityscapes compared to the source model, and is robust to aggressive adaptation and learning rate choices.
Read the full abstract ▾
All authors Chandler Timm C. Doloriel, Yunbei Zhang, Sarthak Kumar Maharana, Muhammad Salman Siddiqui, Tor Kristian Stevik, Fadi Al Machot, Kristian Hovde Liland, Habib Ullah
Computation and Language
Sleight of Word Benchmark: Can Language Models Notice If Their Own Output Was Tampered With?
Alberto Cetoli
The output of a
Language Model can be tampered with while the model is writing it. A simple test can thus be constructed by evaluating the model's perception of this external perturbation. In this spirit, a simple
benchmark is built in which a single word is consistently substituted with another in the generation process. We call this method Sleight of Word. Two distinct axes are measured: metrics that relate to the model's surprise, as well as an evaluation of the textual reaction for 19 different open-weight
language models.
Read the full abstract ▾
Computer Vision
Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting
Chandler Timm C. Doloriel, Yunbei Zhang, Muhammad Salman Siddiqui et al. (+4 more)
Test-time adaptation (TTA) promises robustness under distribution shift by updating a pretrained model on unlabeled test data, but strict online TTA with batch size one and no access to source data is especially prone to drift or collapse. We introduce Sensitivity-Guided Erasing Adaptation (SEGA), a method for strict online continual TTA (CTTA) on corruption-style streams. SEGA uses a small number of structured erasures to probe how predictive
entropy changes as information is removed, and uses the resulting per-sample sensitivity trajectories to coordinate recovery and sample selection rather than relying on raw
entropy or batch statistics. This yields a practical feedback signal for long-horizon batch-size-one adaptation without periodic resets or model reservoirs. In experiments on ImageNet-C, CIFAR10/100-C, and corruption-generated aquaculture streams treated as controlled corruption-style proxies, SEGA yields consistent robustness and stability gains over strong CTTA baselines while reducing backward passes through sensitivity-based gating.
Read the full abstract ▾
All authors Chandler Timm C. Doloriel, Yunbei Zhang, Muhammad Salman Siddiqui, Tor Kristian Stevik, Fadi Al Machot, Kristian Hovde Liland, Habib Ullah
Computation and Language
IndicDetect: Evaluating Cross-Lingual LLM-Generated Text Detection for Hindi, Telugu, and Tamil
Bhaskar Ganesh Devalla, Junchao Wu, Nilesh Dokuparthi et al. (+4 more)
The rapid proliferation of LLMs has further heightened the need to develop dependable AI-generated text detection, especially beyond English. Nevertheless, current
benchmarks pay little
attention to Indic
languages and test detectors in idealized settings that do not represent the real world. We present a generalized
benchmark for AI-generated text detection in Hindi, Telugu, and Tamil, which we call IndicDetect, designed to assess the robustness of detectors under realistic distribution shifts. IndicDetect comprises highly curated human-written texts matched with LLM-generated counterparts across various domains and generators, and systematically evaluates detectors in the presence of domain shift, generator shift, and
adversarial perturbation. Using a single and repeatable evaluation scheme, we evaluate a wide range of statistical and neural detectors. We find substantial robustness failures: supervised neural detectors perform well in-distribution, while training-free methods degrade considerably under unseen generators and
adversarial attacks. The severity of these failures varies across
languages, with Hindi exhibiting the largest overall degradation under
adversarial perturbations. These results highlight that the primary weakness of existing detectors in Indic settings lies in their robustness, not in their peak accuracy. IndicDetect provides standard data splits, an evaluation protocol, and baselines to establish a robust,
language-aware foundation for AI-generated text detection in Indic scripts.
Read the full abstract ▾
All authors Bhaskar Ganesh Devalla, Junchao Wu, Nilesh Dokuparthi, Greeshma Yaluru, Tatiana Muniz Rodriguez, Lidia S. Chao, Derek F. Wong
Computer Vision
FoundYou: A Unified Model for Personalized Segmentation and Retrieval
Gabriele Trivigno, Marcos Alfaro, Claudia Cuttano et al. (+3 more)
Personalized
segmentation and personalized
retrieval both aim to identify the same physical object across different images. While the former localizes the object within a target image, the latter retrieves images where it appears. Despite this shared instance-level objective, the two tasks have largely evolved separately and are addressed with distinct solutions. In this work, we introduce FoundYou, a unified framework built on the observation that Segment Anything 2 (SAM 2), trained to preserve object identity across
video frames, inherently captures instance-level cues. We leverage this property to match objects across independent images, enabling
segmentation and
retrieval to emerge as two outcomes of the same instance
alignment process. This unified view unlocks new capabilities beyond traditional
benchmarks, including few-shot personalized
retrieval and promptable personalized
segmentation with flexible
prompts. Extensive experiments show consistent gains over unified and task-specific methods, including +18.4 mIoU on PerMIS and +17.8 mAP on ILIAS. Performance scales with additional references and remains robust to weaker
prompts. Beyond personalization, FoundYou achieves state-of-the-art results on category-level
retrieval benchmarks. Notably, our approach keeps the SAM 2-small model entirely frozen and adds only 5.9 M trainable parameters, yielding a 52 M-parameter model that is over 75x faster and 20x smaller than the only prior unified solution. Code is available at https://github.com/ga1i13o/FoundYou .
Read the full abstract ▾
All authors Gabriele Trivigno, Marcos Alfaro, Claudia Cuttano, Gabriele Berton, Luis Payá, Carlo Masone
Artificial Intelligence
On the Instance Hardness as a Decision Criterion in TinyML Systems
Tobiasz Puslecki and Krzysztof Walkowiak
TinyML includes the implementation of machine learning on devices with limited
memory and computing resources. With the development of technology, AI systems continue to scale in terms of size and computational requirements. This forces researchers to adapt methods to be environmentally sustainable by designing techniques for reducing computational costs and energy consumption in inferring AI models, even in small devices. In this work, we present preliminary findings on a novel application of the tree depth prune instance hardness method to the TinyML system. The results indicate that threshold control can change energy consumption with limited classification quality changes. This method allows us to adjust classification accuracy, thereby influencing computational complexity and energy consumption for inference. We present a work in progress with initial results as a proof of concept.
Read the full abstract ▾
Computers and Society
Verification-Time Dependency on a Disappearing Evaluator
Ho Wa Ku and Jameel Ahmed Siddiqui
AI governance and assurance often assume that a consequential model-mediated decision can be reconstructed or tested after the fact. That assumption may fail when the evaluator that produced the decision is no longer accessible in the same version and execution context. This paper develops three verification-time constructs derived from Execution Governance (EG) 3.0: Decision-State Commitment, Independent Verifiability, and Counterfactual Auditability. Independent reprocessing of released Study 2 artifacts reproduces two original within-family behavioural comparisons: 52.0% modal-decision reversal for Llama 3.1 8B versus Llama 3.3 70B (26/50) and 30.0% for GPT-OSS 20B versus GPT-OSS 120B (15/50). The corrected baseline establishes that these are within-family comparisons, not provider-established succession. Post-hoc re-pairing against Groq-designated migration paths yields 64.0% and 38.0% reversal, but these figures remain descriptive because the cross-family invocation parameters were asymmetric. A 22-event retirement census independently recomputes to median 16.45 months, mean 18.72 months, range 3.9-40.3 months, with 17/22 intervals below 24 months, while also showing that evaluator availability can differ by service surface. The joint contribution is an operational verification-time protocol and optional Verification-Time Preservation Package (VTPP) specifying what evidence to bind at authorization time, what a separately trusted verifier can substantiate later, how stability and paired counterfactual tests should be calibrated, and which semantic checks remain beyond JSON Schema validity. The protocol is downstream and non-authorizing: it does not alter the EG Core Formula, add a seventh live condition, or state jurisdiction-specific legal admissibility.
Read the full abstract ▾
Computer Vision
Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory
Runjia Qian, Zile Wang, Jihai Zhang et al. (+14 more)
Interactive world models extend
video generation from offline clip synthesis toward persistent simulation of interactive virtual worlds, enabling applications in games, robotics,
embodied agents, and XR. Achieving stable long-horizon interactive generation, however, remains challenging, as the model must simultaneously preserve scene geometry, dynamic consistency, and camera control while supporting real-time autoregressive generation. Building upon
Matrix-Game 3.0, we present
Matrix-Game 3.5, as shown in Figure 1, which advances real-time interactive world generation toward geometry-aware and long-horizon consistent simulation through three key improvements. First, we propose a unified geometry-aware
memory framework, whose patch-
memory and tiled-PRoPE components introduce no additional learnable parameters, combining explicit 3D patch
retrieval with projective camera conditioning to enable geometry-consistent camera control and faithful long-horizon scene recall. Second, we introduce a static-dynamic disentangled world representation that separately models static scene geometry and dynamic subjects, preserving both
geometric consistency and subject identity throughout long-horizon generation. Third, we develop a two-stage progressive real-time
distillation framework that converts a bidirectional
diffusion model into a few-step causal generator through Perceptual Flow Matching and curriculum based Self-Rollout DMD, enabling minute-long real-time interactive generation. Extensive experiments demonstrate that, with a unified training corpus spanning Unreal simulation environments, open-world games, and internet
videos, MatrixGame 3.5 achieves strong performance in long-horizon scene recall, precise camera control, subject consistency,
prompt-driven world generation, and stable real-time open-world interaction.
Read the full abstract ▾
All authors Runjia Qian, Zile Wang, Jihai Zhang, Kai Zou, Wei Yu, Jiaxing Li, Zexiang Liu, Yaokun Li, Fei Kang, Kaichen Huang, Mengyin An, Haobo Zhang, Biao Jiang, Jiahua Wang, Haofeng Sun, Yang Liu, Yangguang Li
Systems and Control
Finite Sample Identification of Analytic Nonlinear Systems
Negin Musavi, Ziyao Guo, Geir E. Dullerud et al. (+1 more)
This paper studies the identification of linearly parameterized nonlinear (LPN) systems. Although LPN systems share the same linear parameterization structure as linear systems, they are more challenging to identify. In particular, previous work has shown, through a counterexample based on a piecewise-affine system, that non-active exploration is generally insufficient for LPN system identification. In this paper, we consider LPN systems with real-analytic feature functions. We show that non-active exploration is sufficient for the identification of this class of systems by establishing non-asymptotic convergence rates of least-squares estimation and set-membership estimation. In addition, we provide counterexamples to show that non-active exploration may not be sufficient for system identification for non-real-analytic systems, even if those systems are infinitely differentiable. We present numerical experiments to further support and validate our theoretical results.
Read the full abstract ▾
All authors Negin Musavi, Ziyao Guo, Geir E. Dullerud, Yingying Li
Machine Learning
Diffusion-Based Inverse Design of Dielectric Resonator Metasurfaces for Shaping Smart Electromagnetic Environments
M. Tsukerman, K. Grotov, D. Vovchuk et al. (+1 more)
Future wireless systems are expected to transform the surrounding space from a passive propagation medium into a smart electromagnetic environment, where engineered surfaces control wave propagation, support wireless sensing, and create programmable electromagnetic fingerprints. A key challenge in realizing this
vision is the inverse design of metasurfaces for tailored electromagnetic propagation. While forward analysis evaluates the response of a known geometry, the inverse task starts from a prescribed scattering signature and seeks a physically realizable structure that produces it. This inverse task is inherently nonlinear and often high-dimensional, while candidate solutions may be non-unique and provide no direct indication of practical realizability. Here, we introduce a conditional
diffusion framework for inverse design of dielectric resonator metasurfaces from target angular scattering patterns. Trained on T-
matrix simulated geometry-response pairs, the model learns a conditional distribution of geometries instead of a deterministic mapping, enabling multiple candidate designs for the ill-posed inverse problem. The best generated metasurface achieves a mean percentage error of 1.39%, outperforming CMA-ES optimization (4.1% after 10 h) while requiring only about one minute for after-training inference. The model also produces lower error distributions than deterministic neural baselines for out-of-distribution spectra, highlighting the potential of
diffusion models for efficient metasurface design.
Read the full abstract ▾
All authors M. Tsukerman, K. Grotov, D. Vovchuk, P. Ginzburg
Information Theory
The generalized covering radii of Melas codes
Shuxing Li and Maosheng Xiong
The generalized covering radii have recently emerged as fundamental parameters of linear codes with applications to database linear querying. In this paper, we study the generalized covering radii $\rho_t(M(m,q))$ of Melas codes $M(m,q)$ over any finite field $\mathbb{F}_q$. We determine $\rho_2(M(m,q))$ for all $q$, and for a general $t \ge 3$, we prove that $\rho_t(M(m,q)) \in \left\{2t,2t+1\right\}$ for $q \in \{2,3\}$ and $\rho_t(M(m,q))=2t$ for $q \ge 4$ whenever $m$ is sufficiently large. These results extend recent work on the covering radius of Melas codes.
Read the full abstract ▾
Computer Vision
OrnaStyler: Ornament-Aware Latent Editing for Content-Preserving 3D Stylization
Tomohiro Aizawa, Shigeru Kuriyama and Chunzhi Gu
Text-guided style editing of 3D assets is essential for adapting existing objects to diverse visual aesthetics in digital content creation. Despite rapid progress in 3D shape modeling, faithfully stylizing an existing asset remains challenging when the desired stylization involves fine-grained structural ornamentation, which requires the model to preserve the source geometry and object identity, while coherently integrating new style-specific details. We propose OrnaStyler, a zero-shot framework for text-guided ornament-aware 3D stylization. Built upon rectified flow-based generative modeling, OrnaStyler introduces an inversion-guided editing strategy that recovers content-aware latent representations at both geometry and appearance levels in a staged manner to facilitate faithful editing. Our core idea is to explicitly model the spatial configuration of stylistic elements, thereby mitigating the fundamental tension between content preservation and style expression in the voxel space. Specifically, at the geometry level, we manipulate voxel representations through flow inversion to synthesize ornament-enhanced structures while preserving the spatial identity of the source asset. Then, at the appearance level, we introduce an adjacency-aware feature inpainting mechanism to harmonize newly generated ornaments with the original content, yielding coherent geometry-appearance integration. Our approach operates solely in the inference phase and enables selective editing over
geometric augmentation or appearance stylization. Extensive experiments on both generated and real-world 3D assets against prior methods demonstrate that OrnaStyler achieves state-of-the-art editing performance in terms of content preservation, style fidelity, and overall visual realism. Code is available at: https://github.com/tomohiro0427/OrnaStyler
Read the full abstract ▾
Computer Vision
Off-Manifold Refinement: Guiding Video Generators with a Frozen World Model
Hai Nguyen-Truong, Tuan-Anh Vu and Dang Huynh
Modern
video generators routinely fail at physical dynamics: objects float, trajectories violate
gravity, contacts vanish. Standard denoising and flow-matching objectives fit visual data distributions but do not explicitly penalize such physical violations. Existing remedies can improve physical consistency, but typically add substantial inference or training cost. Candidate-selection methods generate and score multiple
videos, while gradient-based world-model guidance repeatedly decodes and re-encodes intermediate estimates. Generator-internal refinement adds perturbation and re-denoising loops, whereas post-training requires curated data and additional optimization. We propose Off-
Manifold Refinement (OMR), an inference-time method that instead injects world-model feedback directly into a single sampling trajectory. During scheduled middle ODE steps, we augment the generator velocity with the gradient of an adapter-space V-JEPA 2.1 surprise energy. This external correction can move the latent away from the uncorrected sampling trajectory and toward regions ranked as more physically plausible by the frozen predictor, after which the generator continues rendering from the corrected state. A small trained latent-to-
embedding adapter keeps the gradient tractable at inference, and both the
video generator and the world model remain frozen. On our fixed 400-
prompt VideoPhy-2 detailed subset, OMR lifts the joint Semantic-Adherence-and-Physical-Commonsense metric from 47.0% to 52.0% (+5.0pp absolute, +10.6% relative) over the base Wan2.2-T2V-A14B sampler. On a separate fixed 50-
prompt efficiency subset, it requires $1.71 \times$ the base runtime rather than the multiplicative cost of reward/search alternatives. Project page: https://itruonghai.github.io/omr.
Read the full abstract ▾
Computation and Language
When Less is More: Understanding When Token Filtering Helps and Fails in AI-generated Text Detection
Xiaoyang Han, Lvxiaowei Xu and Ming Cai
The rapid advancement of large
language models (LLMs) has made AI-generated text detection increasingly critical. Existing zero-shot detectors assume that more
token-level evidence leads to more reliable detection. However, our empirical study challenges this consensus: fewer
tokens sometimes work better, retaining only 40% can yield optimal performance, yet this benefit is not universal. Using the
Entropy Gap Score (EGS), we introduce top-$k$ cumulative probability filtering as a diagnostic probe. Across three representative settings, filtering exhibits strikingly different behaviors. We analyze EGS via typical set theory and quantify its dynamics through
entropy calibration and distribution analysis. We find that filtering helps for weak source LMs, where low-
entropy tokens are harmful, but fails for strong source LMs, where they are not notably harmful. Our work provides the first systematic analysis showing that some
tokens are not merely uninformative but systematically harmful due to
entropy miscalibration, revealing a two-sided trade-off in
token-level detection.
Read the full abstract ▾
Game Theory
Fair Division of Graphs: Beyond Traceability
Nicolas Bousquet, Frank Connor, Agnès Totschnig et al. (+1 more)
In this paper, we study fair division problems in which resources are structured as graphs and
agents must receive connected bundles. This connectivity requirement fundamentally alters the problem, making it significantly more challenging than its classical counterpart. We focus on the
fairness notion of $\mathrm{EF1}_{\mathrm{outer}}$, where envy can be eliminated by removing at most one vertex whose deletion does not disconnect the bundle – a critical constraint for applications such as land division and network allocation. Our first result extends prior work by establishing the existence of $\mathrm{EF1}_{\mathrm{outer}}$ allocations for an infinite family of non-traceable graphs (that is, graphs that do not admit a
Hamiltonian path), answering a central open question and generalizing Bilò et al.'s result for traceable graphs. We then make progress on a
conjecture concerning the $\mathrm{EF1}_{\mathrm{outer}}$ spectrum of trees due to Chen and Zwicker. Finally, we complement our structural results with algorithmic insights, showing that deciding the existence of an $\mathrm{EF1}_{\mathrm{outer}}$ allocation is NP-complete even for binary additive valuations, thereby resolving an open complexity question. Taken together, our results deepen the connection between graph theory and fair division, and offer new tools for studying
fairness in structured resource environments.
Read the full abstract ▾
All authors Nicolas Bousquet, Frank Connor, Agnès Totschnig, Sébastien Zeitoun
Machine Learning
INTERVenE: Temporal-Abstraction-Interval Based Transformers for Short-Horizon Medical Event Prediction
Shahar Oded and Yuval Shahar
Electronic Health Record (EHR) prediction models in the intensive care unit must learn from sparse and irregular measurements while preserving the clinical meaning of time and supporting transparent decision-making. We present INTERVenE, a family of
Transformer architectures whose input is an interval-based, knowledge-based temporal abstraction (KBTA), a
token stream of named clinical concepts (states, trends, events, contexts) drawn from a curated medical ontology, rather than an unnamed bin index or a raw measurement triplet. This naming layer is what we ask KBTA to do: it makes the model's per-
token attributions resolve to clinical concepts by construction. INTERVenE offers two complementary variants: an auto-regressive decoder that generates future abstraction trajectories with a per-step risk readout (localizing when and after which events risk rises), and a bidirectional encoder for single-pass joint risk and time-to-event prediction. On 57,078 MIMIC-IV admissions, INTERVenE-Enc outperformed GRU-D, STraTS, and KarmaLego, reaching a support-weighted AUPRC of 0.672 ($+0.046$ over the strongest neural baseline, with non-overlapping 95% bootstrap CIs), AUROC of 0.901, and length-of-stay MAE of 44.4\,h. INTERVenE-Ar complements these predictions with generated abstraction trajectories and evolving risk scores, achieving AUROC of 0.854 and AUPRC of 0.588 under the harder generative readout. An alternative-discretization ablation preserved predictive performance, supporting KBTA's role as a clinically named attribution substrate rather than a prerequisite for accuracy.
Read the full abstract ▾
Computation and Language
REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling
Devrim Çavuşoğlu and Emre Akbaş
Dense
retrieval over long documents is expensive.
Token-level encoders scale quadratically in sequence length, and most long-context
embedding models reach 32K
tokens only through architectural workarounds or by stretching billion-parameter LLMs. We propose REIGN (Refurbished
Embeddings with Integrated Guidance Networks), a contrastively trained bi-encoder that operates on sequences of contextualised chunk
embeddings from a frozen Guidance Network (GN) rather than on raw
tokens. REIGN targets multi-chunk inputs, primarily for document-to-document
retrieval; single-chunk inputs stay with the GN. Decoupling
token-level processing from document-level
reasoning, and caching the GN
embeddings to disk, cuts per-document training cost by roughly four orders of magnitude relative to chunked
Transformer fine-tuning. We also release a synthetic long-document
retrieval benchmark for contrastive training and evaluation at long context lengths. Across an in-distribution Wikipedia
benchmark, the LoCo out-of-distribution suite, and a real-world patent
retrieval case study, REIGN matches dense long-context retrievers at smaller parameter budgets in each regime. A paired significance test puts it on par with models 1.6-4.3x larger on the patent task, and it stays within 0.65 nDCG@10 of a 20x-larger model on LoCo.
Read the full abstract ▾
Computation and Language
When History Is Multimodal: Rethinking Context Management for Long-Horizon Agents
Jiaqi Su, Cong Pang, Jiawei Hong et al. (+4 more)
Long-horizon
agents need a context manager to compress growing interaction histories into a bounded working context, via passive strategies or active strategies that decide how
memory is accessed and reorganized. Meanwhile, prior optical-
memory work mainly treats pixels as a dense codec for textualized histories, often presupposing that rendering context into optical
memory incurs a significant performance drop relative to text, thus coupling this representation with SFT, self-
distillation, or reinforcement learning to close this gap, leaving unresolved (i) how visual rendering performs as a context manager under a fair, controlled comparison, and (ii) whether this carrier offers a native advantage when history is inherently
multimodal. In this paper, we formulate context management as a budget-constrained history transformation and introduce Visual Rendering (VR) as a representational context manager. Under a shared harness, policy model, trigger, and task domain, we evaluate VR on four text-centric and three
multimodal benchmarks against four baselines (No Compression, Discard-All, Sliding Window, Summarization), finding visual
memory is a natural carrier of native visual evidence. Building on this finding, we propose VERA (Visual Evidence-Retaining strategy for long-horizon
Agents), a training-free context manager built on deterministic rendering with no exposed
memory operations: on text-centric
benchmarks it renders textual history as VR does, while on
multimodal benchmarks it retains native visual observations instead of translating them into text. Across nearly all
benchmarks, VERA cuts cumulative non-cache
tokens by 31.5%-63.1% versus No Compression, matches existing managers on text-centric tasks, and achieves the highest accuracy among all baselines on
multimodal tasks, supporting a modality-preserving view of long-horizon context management.
Read the full abstract ▾
All authors Jiaqi Su, Cong Pang, Jiawei Hong, Tiankuo Yao, Zixuan Chen, Xin Lou, Lewei Lu
Robotics
EMERGE-Policy: A Robot Mind Emerges Beyond a Single Policy
Zhirui Fang, Qingchi Yu, Ziyang Chen et al. (+18 more)
A
robot's effective “mind” need not reside in a single policy. It can emerge when specialized components perceive, reason, predict, act, verify, and remember within a shared orchestration process. EMERGE-Policy turns this perspective into a graph-structured agentic framework that coordinates both capability invocation and information exchange. A Main
Agent retains task-level state within an active context window, while role-specific Sub
Agents process perception, execution monitoring, verification, and
memory consolidation in isolated contexts and return structured, task-relevant evidence. Role-specific contexts control information load by exposing only decision-relevant evidence to the Main
Agent, while the functional Skill interface composes heterogeneous backends as Operational, Imagination, and Evaluation Skills. Criterion-grounded verification, textual failure diagnosis, and Branch Stack recovery provide localized correction, with
token-aware external
memory preserving task-relevant state. Together, their closed-loop interaction realizes the system-level policy captured by the name EMERGE-Policy. Without additional fine-tuning, we achieved outstanding performance on several public
benchmark that have had a wide-reaching impact, and conducted a series of real
robot experiments. These system-level results suggest that through the division of different functional sub-tasks among multiple
agents and their concurrent collaboration, as well as the technical paradigm where the model is regarded as a skill and called within the framework, EMERGE-Policy can extend the robust
robot policies beyond isolated runs.
Read the full abstract ▾
All authors Zhirui Fang, Qingchi Yu, Ziyang Chen, Longfei Li, Haoran Ma, Keru Zhou, Xinrun Xu, Samith Va, Yuxuan Hu, Peixuan Song, Qiang Du, Bin Qian, Yongkang Deng, Xin Li, Yezhen Wang, Zhe Li, Hao Luo, Shuyan Li, Ziwei Wang, Weijian Deng, Xiu Li
Machine Learning
Joint Spatiotemporal Spectral Neural Operators for Learning PDEs on Irregular Domains
Abdolmehdi Behroozi and Chaopeng Shen
Learning solution operators for partial differential equations (PDEs) on irregular and geometry-dependent domains remains a central challenge in scientific machine learning. While spectral methods provide strong inductive biases for modeling global interactions, they are typically limited to regular domains, and existing neural approaches often require domain warping, interpolation, or costly
geometric embeddings. We introduce the Graph Spectral Neural Operator (GSNO), a neural operator that combines spatial graph spectral decompositions with temporal
Fourier transforms through a unified space–time spectral kernel. This formulation enables globally coherent operator learning on non-Cartesian discretizations without domain warping or autoregressive rollouts. By replacing learned
geometric embeddings with a graph
Laplacian spectral basis, GSNO provides geometry-aware spectral learning with low parameter complexity. Across steady and unsteady PDE
benchmarks on irregular and geometry-dependent domains, GSNO achieves strong accuracy with reduced runtime and parameter counts, while demonstrating robust zero-shot generalization across mesh resolutions and geometry families.
Read the full abstract ▾
Computer Vision
MASQ: Mask-Aware Spatiotemporal Quantization for Unsupervised Skeleton Action Segmentation
Xinyao Qin, Linxiang Peng, Youbao Ye et al. (+2 more)
Unsupervised skeleton-based temporal action
segmentation is a crucial task for understanding human behavior in long untrimmed sequences. Recent approaches often rely on discrete quantization to discover action boundaries from motion representations. However, when spatial masking is introduced for representation learning, it can introduce representation ambiguity, while discrete quantization further amplifies small fluctuations in the latent space. The interaction between these two factors often leads to unstable code switching and severe temporal jitter near action boundaries.To address these limitations, we propose a novel Mask-aware Action Spatiotemporal Quantization (MASQ) framework. Our framework decouples the conflicting tasks of spatial feature inference and temporal smoothing.In the spatial dimension, we introduce a Joint-Level Structured Dropout (JLSD) mechanism that masks the entire temporal trajectory of selected joints, to encourage the model to learn discriminative inter-joint coordination patterns. In the temporal dimension, we design a mask-aware velocity loss that enforces motion consistency only on visible joints, that prevents gradient conflicts caused by masked signals and stabilizing temporal predictions. Extensive experiments on three widely used skeleton
datasets, including HuGaDB, LARa, and BABEL, demonstrate that the proposed MASQ framework significantly outperforms existing state-of-the-art unsupervised methods. In particular, our model establishes a comprehensive and substantial leading advantage in the Mean over Frames accuracy.
Read the full abstract ▾
All authors Xinyao Qin, Linxiang Peng, Youbao Ye, Di Yang, Jiangtao Wang
Computation and Language
En-ViMedNER: An English-Vietnamese Parallel Biomedical Corpus with UMLS Semantic Type Annotations
Nhu Vo, Phuong Nguyen, Nu Uyen Phuong Le et al. (+4 more)
Biomedical Named Entity Recognition (NER) is fundamental to healthcare AI applications, including clinical decision support and medical information extraction. While corpora with Unified Medical
Language System (UMLS) annotations, such as MedMentions, have driven progress in English biomedical NER, no comparable resource exists for Vietnamese. This paper presents En-ViMedNER, the first English-Vietnamese parallel biomedical NER corpus annotated with UMLS semantic types, which are
language-neutral codes providing a shared cross-lingual label space and ensuring direct comparability with existing UMLS-based resources. The corpus contains 4,392 PubMed abstract pairs, 44,892 English-Vietnamese sentence pairs, and 202,949 aligned entity-mention pairs across 21 semantic types adapted from the MedMentions ST21pv
dataset. To balance quality and scalability, we have constructed the corpus through automatic translation, expert post-editing, LLM-assisted label projection, and human verification and adjudication. We characterize En-ViMedNER as a large-scale silver-standard corpus with a human-audited and consensus-corrected mini-test subset. We evaluate En-ViMedNER in two settings: (i) Vietnamese-input/Vietnamese-output biomedical NER and (ii) English-input/Vietnamese-output cross-lingual NER. For Vietnamese NER, we
benchmark Vietnamese-supervised encoder models, English-supervised
multilingual encoder models, and
prompt-based LLMs. The best model achieves an F1 score of 52.70 on the test set and 53.78 on the mini-test set. For cross-lingual NER, we
benchmark encoder-decoder models and
prompt-based LLMs. The best model achieves an F1 score of 45.44 on the mini-test set. We publicly release our corpus, corpus construction pipeline, and baseline models to facilitate future Vietnamese biomedical NLP research.
Read the full abstract ▾
All authors Nhu Vo, Phuong Nguyen, Nu Uyen Phuong Le, Inigo Jauregi Unanue, Dung D. Le, Massimo Piccardi, Wray Buntine
Computation and Language
VibeJam: A User Study Platform for Web Development with Agents
Nishant Balepur, Connor Baumler, Valerie Chen et al. (+3 more)
Programming with AI is increasingly agentic, users
prompt LLMs to directly edit their code and review the changes, with adoption growing especially for web development tasks. Despite this growth, most NLP work uses offline evaluation and lacks support for online studies, losing insights into how programmers truly use coding
agents. We release VibeJam, a browser-based user study platform for users to collaborate with AI
agents to develop websites. VibeJam enables
agent customization and uses the open-source Aider
agent by default, and to mirror downstream use, we add diff review, chat and plan modes, and live website previews. In a pilot study with 55 released, game-based website creation tasks, five experienced AI programmers rate our system as fun, simple, and resembling commercial tools, while 13 junior students use VibeJam to make websites of higher quality than
agents in the same task. We open-source VibeJam to spur extensions and support studies on how coding
agents can help users.
Read the full abstract ▾
All authors Nishant Balepur, Connor Baumler, Valerie Chen, Eunsol Choi, Rachel Rudinger, Jordan Boyd-Graber
Machine Learning
Sensitivity-Constrained Neural Operators for Data-Efficient Forward and Inverse Modeling of Partial Differential Equation Systems
Abdolmehdi Behroozi, Chaopeng Shen, Daniel Kifer et al. (+1 more)
Neural operators provide fast surrogates for partial differential equation (PDE) solvers, but their reliability can degrade for high-dimensional spatial inputs and inverse or repeated inference. State-only training constrains solution values but not the learned input–output response. We study sensitivity-constrained neural operators (SC-NOs), which augment standard training with sampled solver-derived Jacobian supervision. Selected sensitivities from differentiable solvers or discrete adjoints are matched during training, allowing response information to be amortized across minibatches without imposing the full Jacobian at every update. We evaluate SC-NO on advection–
diffusion and RANS–Spalart–Allmaras
benchmarks, input-dimensionality scaling tests, long-horizon autoregressive rollout, and a shallow-water Tohoku tsunami source-inversion case. Sensitivity supervision improves forward prediction and yields larger gains in gradient-based inverse reconstruction of distributed fields. Scaling experiments show an improved accuracy–cost tradeoff for high-dimensional gridded inputs, while ablations indicate that state values and Jacobian information provide complementary supervision. In the tsunami case, SC-FNO reconstructs gridded seafloor deformation from sparse early gauge observations and forecasts subsequent wave propagation in a near-real-time proof-of-concept workflow. These results support sampled sensitivity supervision as a practical way to improve neural PDE surrogates when forward accuracy, inverse stability, robustness, and computational cost must be considered together.
Read the full abstract ▾
All authors Abdolmehdi Behroozi, Chaopeng Shen, Daniel Kifer, Kathryn Lawson
Computation and Language
Check The Scoreboard: An Analysis of Scoring Schemes on Multiple-Choice Evaluation
Nishant Balepur, Paiheng Xu, Wei Ai et al. (+3 more)
Multiple-choice question answering (MCQA)
benchmarks in NLP use number-right scoring (accuracy), but in educational testing, the scoring scheme, the combination of the response mode models follow and the rule for grading responses, is a key design choice that dictates which abilities to reward. We examine how alternatives to number right change what MCQA measures with six education-inspired schemes that assess abilities beyond accuracy: distractor elimination, abstention, confidence calibration, and self-correction. On LLM
benchmarks, these schemes: 1) shift rankings of 31 LLMs beyond rephrased number right
prompts; 2) better predict the LLMs users prefer in LLM Arena; and 3) reveal distinct model capabilities, like that GPT-5 rarely abstains and readily self-corrects, while weaker open-weight models often abstain and hesitate to eliminate choices. Given the benefits of alternative scoring schemes, we discuss ways to extend them to tasks beyond MCQA.
Read the full abstract ▾
All authors Nishant Balepur, Paiheng Xu, Wei Ai, Eunsol Choi, Rachel Rudinger, Jordan Boyd-Graber
Machine Learning
Structural Hierarchy and Geometry in Molecular Representation Learning
David Sulu, Lorenzo Di Fruscia and Jana M. Weber
Molecular self-supervised learning uses chemical structures to guide which molecular
embeddings should be similar. We study whether explicitly encoding a molecule's Bemis-Murcko scaffold and using it to supervise the molecular
embedding changes what the model learns. We further test whether this effect depends on the
embedding geometry by comparing Euclidean and Lorentz contrastive objectives. Across two augmentation strengths, scaffold-supervised models consistently organize molecules according to both identical and structurally related scaffolds. The resulting
embeddings also improve molecular property prediction on several tasks, while the exact gains depend on the predicted property. The effect of scaffold supervision on molecular organization is stronger under Lorentz objectives, but neither geometry provides a consistent overall advantage. These results show that explicitly teaching the relation between a molecule and its structural core can reliably shape the organization of molecular
embedding space, while the extent of usefulness of this organization remains task dependent.
Read the full abstract ▾