Computation and Language
SMI: Ontology-Grounded Semantic IDs for Hierarchy-Aware Medical Concept Representation
Ziyang Song, Lia Shen, Yixuan Li et al. (+6 more)
Biomedical
language models (LMs) provide strong representations for clinical tasks, but they often fail to capture the hierarchical structure among medical concepts. This limitation is especially pronounced for rare and fine-grained clinical codes in long-tailed vocabularies, where hierarchy-agnostic LM representations become less informative as concept frequency decreases. We introduce Semantic Medical Identifier (SMI), a training-free framework for constructing ontology-grounded Semantic IDs and hierarchy-aware medical concept representations. For each diagnosis, procedure, or medication concept, SMI defines its Semantic ID as the coarse-to-fine path through an expert-defined medical ontology. SMI then aggregates frozen biomedical LM
embeddings across the corresponding ontology levels to form hierarchy-aware medical concept representations that preserve coarse-to-fine clinical semantics. The base SMI uses uniform aggregation across ontology levels, while a level-weighted variant selects global level weights on validation data. Our theoretical analysis shows that SMI yields more informative medical concept representations than hierarchy-agnostic LM
embeddings, particularly for rare and fine-grained clinical concepts. Experiments show that SMI captures meaningful hierarchical structure and improves clinical relation prediction. On MIMIC-IV, SMI improves mortality prediction, readmission prediction, drug recommendation, and rare drug prediction. On eICU, SMI yields more robust patient representations under cross-hospital distribution shift.
Read the full abstract ▾
All authors Ziyang Song, Lia Shen, Yixuan Li, Qincheng Lu, Weihao Li, Haoran Xu, He Zhu, Xinyu Wang, Yue Li
Robotics
Perception Beyond the Visible: Incompleteness-Aware Scene Understanding for Robot Autonomy
Rohit Mohan
Reliable
robot autonomy requires
reasoning about the world from partial and noisy observations. However, many perception systems model only visible scene regions, rely on fixed semantic categories, and assume reliable sensor measurements. These assumptions break under occlusion, novel object encounters, and sensor degradation. In this paper, I present a research
vision for incompleteness-aware scene understanding. I organize this
vision around three fundamental challenges: incomplete evidence, incomplete knowledge, and incomplete sensor reliability. I discuss my research contributions toward addressing these challenges through amodal perception, semantic occupancy forecasting, open-world scene understanding, label-efficient learning, and uncertainty-guided multi-modal fusion. Building on these contributions, I outline future research directions toward belief-centric 4D scene representations. These representations aim to jointly model geometry, semantics, motion, and uncertainty. I also discuss active sensing and safe adaptation strategies that allow
robots to reduce uncertainty through interaction. The goal is to develop calibrated and actionable scene representations that support reliable autonomy in dynamic, open-world environments.
Read the full abstract ▾
Computation and Language
Known-Voice Cloning and the Limits of Personality Transfer for Character Design
Johanna Magdalena Kuch, Maud van Lier, Daksitha Senel Withanage Don et al. (+3 more)
Recent advances in zero-shot voice cloning systems make it possible to reproduce a recognizable voice from a short recording and attach it to arbitrary virtual characters. Prior work suggests that familiar vocal identity can carry over associated personality impressions to new targets such as
robots or virtual characters. However, these works have mainly examined familiarity and personalization effects rather than directly testing whether a cloned familiar voice systematically transfers personality impressions to an embodied virtual character. Such transference raises the concern that cloned voices could be used to manipulate people into engaging with virtual characters as capable social actors. Across two studies, we investigated whether personality impressions transfer when a virtual character speaks with the cloned voice of a familiar person. Study 1 examined this question in a real-world university setting using the cloned voice of a lecturer familiar to the participating students. Study 2 examined the same question online using voices of social media content creators and members of their communities. Drawing on the concepts of identity activation, trait transfer, and person reconstruction, we show that evidence of personality transfer was limited in both studies. Observed effects were selective and did not generalize across traits or study contexts. In the online study in particular, recognizable voice identity cues activated expectations about the speaker but did not reconstruct the broader person impression. Qualitative responses further indicated that judgments were frequently shaped by perceived artificiality and by whether voice and appearance fit together. Our findings moderate common concerns that cloned voices straightforwardly manipulate people into perceiving artificial characters as capable social actors.
Read the full abstract ▾
All authors Johanna Magdalena Kuch, Maud van Lier, Daksitha Senel Withanage Don, Patrick Gebhard, Tanja Schneeberger, Elisabeth André
Social and Information Networks
When Platforms Pay Users to Correct Misinformation: Revenue Incentives and Governance Capacity in Weibo Annotations
Chichen Lin, Huaijin Xie, Wenhan Xie et al. (+5 more)
Crowdsourced misinformation governance systems such as Community Notes and Weibo Annotations depend on sustained corrective labor. How monetary incentives shape participation and subsequent governance outcomes remains poorly understood. We conduct a mixed-methods study of Weibo Annotations, analyzing 102,994 posts and 431,407 comments from 2023–2026, alongside interviews with 15 contributors. We find concentrated corrective labor, limited observed display, and weak quality–engagement
alignment. Policy introduction was associated with sharp increases in contributor participation and annotation production. Model-assisted quality followed its expected trajectory, evidence for additional display growth was inconclusive, and engagement per annotation fell below expectation. Public discussions and interviews reveal substantial verification demands, difficult-to-interpret review processes, uneven platform knowledge, and gaps in contributor protection. We identify four recurring bottlenecks in governance orchestration: participation, review, reach, and protection. Effective incentive design therefore depends on whether platforms can support these downstream processes as corrective labor expands.
Read the full abstract ▾
All authors Chichen Lin, Huaijin Xie, Wenhan Xie, Weijian Fan, Xiao Han, Yijie Jin, Xiaojie Hao, Jiaying Wu
Computer Vision
PlanPath: Exploration-Guided Orchestration for Patient-Level Pathology Reasoning
Jiusong Ge, Mingzhao He, Qidong Liu et al. (+8 more)
A patient's pathology case spans tens of slides from distinct specimens and anatomical sites, each carrying non-redundant, site-specific evidence. Forming a patient-level conclusion therefore requires locating the slides relevant to a given question and integrating complementary findings across them. However, existing pathology
agents analyze one slide at a time and describe morphology rather than measure it, leaving evidence acquisition across a patient's specimens and patient-level quantification underexplored. To address this gap, we propose PlanPath, an agentic framework for patient-level pathology visual question answering (VQA). PlanPath turns the question into an exploration plan that specifies the evidence required, routes to the slides likely to carry it, and drives coarse-to-fine acquisition from tissue architecture down to individual
cells. Tissue- and
cell-level tools supply the counts, proportions, and extents, which PlanPath aggregates across slides into a traceable answer. To enable evaluation, we build two patient-level VQA
datasets for renal and gastric cancer, averaging 15 WSIs per patient, with pathologist-verified question-answer pairs derived from diagnostic reports. Experimental results show that PlanPath outperforms the strongest baseline by 9.4% and 12.1% in overall accuracy on the two
datasets and further improves existing slide-level
agents when plugged into our framework. The
dataset and code are available at: https://github.com/JSGe-AI/PlanPath_1.
Read the full abstract ▾
All authors Jiusong Ge, Mingzhao He, Qidong Liu, Chunbao Wang, Chunze Yang, Di Zhang, Jiashuai Liu, Mireia Crispin-Ortuzar, Huazhu Fu, Chen Li, Zeyu Gao
Cryptography and Security
ARACDE: Retrofitting Databases with ABAC using External Authorization Engines
Karthikeya S M Yelisetty, Shamik Sural and Santosh Nagarakatte
This paper proposes a methodology for decoupling the authorization logic of a relational database from its core data management engine, enabling specification of advanced access control policies with minimal changes to the code base. Our decoupled authorization architecture, which we call ARCADE, externalizes access request resolution to a formally verifiable policy engine (e.g., Cedar), while the database itself enforces those decisions. We showcase the capabilities of ARCADE on two widely popular open-source databases, namely MySQL and PostgreSQL. Purpose built lightweight plugins add an Attribute-based Access Control (ABAC) layer that augments the native discretionary and role-based access control capabilities of these databases. ARCADE supports highly expressive policies using attributes of subjects, objects, and the environment, and the use of Cedar enables easy auditing and verification of the specified policies. It follows a design principle that mitigates potential risks in segregating authorization from the database core through low footprint, network isolation, and a policy composition methodology that does not negate any native authorization. Experiments on TPC-C, TPC-B, and a custom workload show that ARCADE incurs negligible performance overhead, for instance, less than 3.9% throughput penalty for MySQL (1.3% for PostgreSQL) on industry standard TPC-C
benchmark.
Read the full abstract ▾
Machine Learning
BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling
Mengyu Li, Qianqian Qu and Jun S. Liu
Generative models are often required to serve many downstream conditional tasks. In the training-free setting, a pretrained unconditional model is reused as a prior and combined with a task-specific likelihood to sample from the corresponding posterior. While such training-free samplers have been developed for
diffusion and flow models, their counterpart for Schrödinger bridge (SB) models remains unexplored, despite the growing appeal of SBs as flexible
stochastic transport models between general source and target distributions. We propose BridgeTwist, a training-free conditional sampler for pretrained SB generative models, formulated as a tempered twisted sequential Monte Carlo scheme. Its twist is a closed-form plug-in surrogate, obtained by combining the velocity and score fields exposed by SB pretraining into an endpoint predictor and evaluating the likelihood there. Since this surrogate is less reliable near the source, we temper the twist with a time-varying exponent, downweighting its influence at early steps. We further introduce a bridge-shaped inference-time
diffusion schedule that concentrates the proposal noise in the interior of the path. Telescoping importance weights then cancel all intermediate twist factors, yielding an asymptotically exact sampler for the posterior. Empirically, BridgeTwist outperforms training-free baselines on class-conditional and text-prompted image generation, and is competitive with specialized inverse problem solvers on inpainting, deblurring, and super-resolution.
Read the full abstract ▾
Machine Learning
Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback
Weida Liang and Kenji Kawaguchi
Language model systems repeatedly make test-time decisions by comparing similarity: they retrieve exemplars, rank candidates, and revise responses. Yet similarity is not unique: lexical, semantic, structural, and stylistic resemblance can point to different candidates, and the task-aligned notion can change across instances. We introduce BASIS (
Bayesian Axis Selection via Interactive Signals), a training-free
Bayesian method that uses weak test-time feedback to infer which criterion in a supplied, task-specific library governs the current decision. It maintains a joint posterior over candidate targets and criteria, updates it from scalar scores, pairwise preferences, or verifier outputs, and selects probes by expected information gain. In a finite noisy model, we characterize when the target-criterion pair is recoverable and show why fixed-criterion and fixed-mixture rules can fail under criterion shift. Across concept recovery,
reasoning exemplar selection, and response refinement, BASIS improves six-probe concept-recovery Success@1 from 56.0% to 68.1%,
reasoning accuracy from 72.3% to 73.1%, and refinement win rate from 61.4% to 63.8% over tuned static mixtures. It also exceeds compute-matched best-of-N selection on
reasoning (72.1%) and refinement (61.2%). Gains are largest under criterion mismatch and with larger candidate pools, and matched controls indicate that adaptive criterion weighting explains much of the benefit, with joint target-criterion inference adding further value. BASIS selects only among supplied criteria and does not discover new ones.
Read the full abstract ▾
Computer Vision
Texture Interpolation as Texton Matching
Ido Madar, Gal Oren and Shai Avidan
Texture interpolation asks what should lie between two textures. Standard methods typically blend pixels or features at corresponding spatial locations, implicitly assuming that co-located elements should be mixed. For unrelated textures, however, this correspondence is arbitrary: a crack at one location has no particular relationship to a fiber at the same location in another image. We study whether this hidden pairing choice is itself a major determinant of interpolation quality. We represent textures as collections of local appearance vectors, or textons, and replace positional pairing with appearance-aware matching while keeping the encoder, representation, and decoder fixed. This isolates the effect of correspondence from changes in model capacity or training. Across texture pairs, appearance-aware matching consistently improves the distributional quality of interpolated midpoints over positional feature blending. Soft matching produces the strongest midpoint statistics, whereas one-to-one assignments yield more balanced transitions and closer agreement with the target endpoint. The same intervention also improves a second pretrained texture interpolator without retraining. These results identify correspondence as a first-class design choice in texture interpolation: meaningful transitions depend not only on how strongly two textures are mixed, but also on which local appearances are mixed with one another.
Read the full abstract ▾
Machine Learning
Kwai Summary Attention V2 Technical Report
OneRec Team, Chenglong Chu, Guohong Mu et al. (+30 more)
Summary-
token architectures such as Kwai Summary
Attention (KSA) compress distant context into learnable Summary
token per chunk, and hybrid variants interleave these layers with full
attention to retain exact access to the original text. In such hybrid KSA-Full architecture, the interleaving inserted summary
tokens are served as a streaming flow role across different layers. Although effective, however, it also introduce some bottlenecks: (1) the different layers summary compression chunk must be same, therefore hard to reach a flexible KV Cache compression, e.g., different layer set different summary compression chunk window. (2) in the full-
attention layers, the summary
token introduced additional computation cost, but such layer ignore them and still pay quadratic prefilling, therefore unfriendly to the computation side. Motivated by them, we developed the KSA V2, which not only achieves a more flexible KV cache
memory compression but also reduces the computation cost in Full
attention layer. Specifically, we found that the summary
tokens can serve two roles: the KV
memory and sparse indexer.
Read the full abstract ▾
All authors OneRec Team, Chenglong Chu, Guohong Mu, Guowang Zhang, Hao Peng, Hui Wang, Jian Liang, Jiangxia Cao, Jiao Ou, Jiaxin Deng, Lu Ren, Muhao Wei, Ruiming Tang, Tianle Xu, Wenwu Ou, Xingmei Wang, Zhixin Ling, Zhiyuan Liang, Ziqi Wang, Chaoyi Ma, Haixiao Gao, Kuo Cai, Renpu Liu, Ruochen Yang, Wenlong Xu, Xinqi Jin, Yan Sun, Yifan Wang, Yingzhi He, Yiyu Wang, Yusen Huo, Zhaojie Liu, Zihan Zhou
Sound
AMemOps: Evaluating Memory Updates in Long Audio Streams
Peiwei Chang, Li Zhang, Mark D. Plumbley et al. (+2 more)
Audio
memory must recognise recurring sources across acoustic changes while keeping their attributes up to date. Overall accuracy does not reveal how these demands interact. We introduce Audio
Memory Operations (AMemOps), a
benchmark for latest-attribute
retrieval, preservation of unchanged attributes and absent-source rejection in long audio streams. Paired controls vary recordings, training identities and earlier events to examine their effects on updating. Training on other recordings of the test instruments increases a reference delta-rule
memory's update advantage over matched
attention by 13.4 percentage points. At
retrieval delays of 120\,s, matched histories separate benefits of consistent repetition from costs of conflicting earlier values, while additive-
memory controls identify benefits of erasure.
Read the full abstract ▾
All authors Peiwei Chang, Li Zhang, Mark D. Plumbley, Philip J.B. Jackson, Wenwu Wang
Machine Learning
Does Pretraining Teach Chemical Language Models Chemistry?
Leif Sieben and Yoel Zimmermann
Chemical
language models (CLMs) are pretrained on large corpora of molecules with the aim of learning representations that transfer to diverse downstream tasks. Here, we systematically study the effects of pretraining using a series of such CLMs across 64 molecular property prediction
datasets. We find that the downstream gains of pretraining in CLMs do not scale and performance saturates below gradient-boosting baselines. Across the regimes evaluated, only supervised pretraining on traditional physico-chemical descriptors consistently improves downstream performance for the CLMs tested whereas some forms of pretraining result in models worse than a randomly initialized encoder. While models can resolve molecular structure well, they do so no better than a randomly initialized model, suggesting that, at best, CLMs learn descriptor-like properties in addition to low-level
token statistics during pretraining, but surprisingly little chemistry beyond what classical molecular features already capture.
Read the full abstract ▾
Robotics
ForkCast: Predictive Recovery for Vision-Language-Action Policies via Counterfactual Futures
Chenru Wen, Huajian Zeng, Haokai Ding et al. (+5 more)
Vision-
language-action (VLA) policies perform manipulation tasks using camera images and
language instructions, but object slip or visual occlusion can disrupt execution. Recovery is typically learned during policy training or delegated to a monitor that triggers a scripted repair after detecting a failure. We introduce ForkCast, a predictive recovery framework that compares counterfactual futures to determine whether and how to intervene in a frozen VLA policy. At each decision point, ForkCast evaluates three candidates: executing the policy's nominal action chunk (Commit), adjusting the camera viewpoint (Reobserve), and replanning the arm trajectory (Replan). A candidate-conditioned world model forecasts the latent outcome of each candidate at a common future horizon, and a shared task-progress head scores the predicted outcomes. By evaluating the policy's own continuation alongside the repair candidates, a single comparison based on task progress determines both whether and how to intervene, without a failure detector, an intervention threshold, or updates to the VLA backbone. On five simulated RoboTwin 2.0 tasks with injected occlusion and object slip, ForkCast increases pooled success from 13.3% for the frozen $\pi_{0.5}$ policy to 30.0% and transfers to two additional VLA backbones without updating ForkCast. After adaptation on real-
robot candidate rollouts, ForkCast also improves success over the base policy under both clean and visibility-limited conditions. Code will be released to benefit the research community.
Read the full abstract ▾
All authors Chenru Wen, Huajian Zeng, Haokai Ding, Jian Kang, Anqing Duan, Dawei Zhou, Dezhen Song, Xingxing Zuo
Machine Learning
Tiny Recursive Message Passing
Tommaso Salvatori, Matteo Forasassi, Alexis Toumi et al. (+1 more)
Message passing neural networks have shown remarkable performance in algorithmic and constraint
reasoning, due to their ability to encode the structure of the task directly in the architecture. Recent work has shown that better results can be achieved using recursive
transformers trained with deep supervision and truncated recursions, which make extremely deep loops stable to train, and equipped with test-time procedures such as discrete deduction
lattices. In this work, we apply the same procedures to message passing networks, and show that the two ingredients are complementary, and lead to parameter efficient models: we obtain about $99\%$ test accuracy on Sudoku-Extreme with a model of $16$k parameters that trains in about $10$ minutes on an H100, or in $9$ hours on a CPU. We further show that the cost of truncating gradients grows with the number of rounds information needs to cross the graph, making the choice of wiring a trade-off between robustness to truncation and transfer across problem sizes. We conclude by showing that our models transfer zero-shot to larger instances than those seen during training, outperforming popular neural baselines on N-queens and Boolean satisfiability with a fraction of their parameters.
Read the full abstract ▾
All authors Tommaso Salvatori, Matteo Forasassi, Alexis Toumi, Giovanni de Felice
Computer Vision
ST-GRU PredRNN-V2: A GRU-Based Reformulation of PredRNN-V2 for Video Prediction
Augusta van Haren, Hanna Hoogen, Luca Pattavina et al. (+1 more)
Video prediction requires models to capture complex spatiotemporal dependencies and to retain relevant information over long sequences. PredRNN and its successor PredRNN-V2 address this challenge with spatiotemporal Long Short-Term
Memory (ST-LSTM) units that maintain two separate
memory states, at the cost of a relatively complex recurrent building block. In this work, we investigate whether the simpler gating of Gated Recurrent Units (GRUs) can be transferred to spatiotemporal predictive learning. To this end, we develop a spatiotemporal GRU (ST-GRU) unit as a GRU-based alternative to the ST-LSTM. The ST-GRU replaces the ST-LSTM's three gates per
memory state with two GRU-style gates (update and reset), and merges the temporal
memory state into the hidden state, which reduces the number of parameters by about 5%. We incorporate the ST-GRU into PredRNN-V2 and evaluate the resulting model on the Moving MNIST
video prediction
benchmark, following the original experimental protocol. Averaged over ten predicted frames, the ST-GRU-based PredRNN-V2 achieves an MSE of 55.1, an SSIM of 0.883, an LPIPS of 0.065 and a PSNR of 19.53dB. It does not surpass the original ST-LSTM-based PredRNN-V2 on MSE, SSIM or PSNR, but it achieves a lower LPIPS and performs on par with the earlier ST-LSTM-based PredRNN, while using a simpler recurrent
cell. These results suggest that ST-GRUs are a promising building block for spatiotemporal predictive learning and motivate further work on their design and integration.
Read the full abstract ▾
All authors Augusta van Haren, Hanna Hoogen, Luca Pattavina, Quincy Rommen
Machine Learning
MultiAlloc: Budget-Aware Precision Allocation for KV Cache Quantization
Yangchengyu Zhou, Zhiping Wu, Runchang Jiang et al. (+5 more)
The Key-Value (KV) cache constitutes a dominant source of
memory consumption during large
language model (LLM) inference, particularly in long-context and complex
reasoning scenarios. Existing KV cache quantization methods have explored different compression granularities, including layer-wise precision adjustment and
token-level information preservation. In practical deployment, however, the key challenge is not merely compression, but how to allocate limited quantization resources among heterogeneous precision preservation strategies under a fixed KV cache
memory budget. We propose MultiAlloc, a profiling-guided precision allocation framework for KV cache quantization that adaptively distributes limited quantization resources between layer-wise precision enhancement and
token-wise preservation. MultiAlloc employs lightweight offline profiling to characterize layer sensitivity and
token importance, enabling adaptive precision allocation under a fixed
memory constraint. Guided by the profiled
memory–accuracy trade-off, it automatically derives an effective precision allocation strategy without online allocation search, and applies the resulting policy during inference. Extensive experiments on
reasoning and long-context
benchmarks demonstrate that MultiAlloc consistently improves over layer-wise,
token-wise, and recent multi-granularity KV cache quantization methods under matched
memory budgets across diverse models, including Mistral, Llama, DeepSeek-Qwen, and QwQ.
Read the full abstract ▾
All authors Yangchengyu Zhou, Zhiping Wu, Runchang Jiang, Dongdong Ren, Youfang Han, Wei Zhao, Dongqi Cai, Wenbin Li
Networking
HILO: Enabling Low-power, Dual-Band Communication using Tunnel Diode Oscillators
Dhairya Shah, Rajashekar Reddy Chinthalapani, Pramuka Sooriya Patabandige et al. (+1 more)
Wireless communication remains the most power-consuming operation in embedded systems. Low-power transmitters such as backscatter achieve microwatt-scale operation but produce weak signals susceptible to in-band interference and frequency-selective fading, particularly in non-line-of-sight settings. Multi-band transmission can mitigate these effects through spectral-domain redundancy rather than temporal-domain redundancy, improving reliability without sacrificing bitrate or latency. However, conventional multi-band
radio transceivers require duplicated RF chains or power-hungry synthesizers. We introduce HILO, a tunnel diode-based frontend that enables dual-band operation from a single
circuit. HILO inverts the conventional paradigm: rather than suppressing the harmonics inherent to tunnel diode nonlinearity, it harnesses them. An external device injection-locks the oscillator to a fundamental frequency, simultaneously stabilizing a higher harmonic and yielding two injection-locked carriers without a second oscillator or frequency multiplier. In transmit mode, HILO exploits self-oscillating mixing to modulate both carriers simultaneously; in receive mode, it uses autodyne downconversion at both frequencies. By turning an inherent nonlinearity into a feature, HILO achieves dual-band links while consuming under 210 $\mu$W.
Read the full abstract ▾
All authors Dhairya Shah, Rajashekar Reddy Chinthalapani, Pramuka Sooriya Patabandige, Ambuj Varshney
Networking
Pedestrian Trajectory Prediction through LoRA Federated Training
Simone Travagliati and Maria Luisa Merani
In Intelligent Transport Systems, protecting vulnerable road users, specifically pedestrians, is a paramount challenge. The present work contributes to this field, putting forth a distributed architecture in which vehicles connected to the cellular infrastructure collect pedestrians' trajectories and fine-tune a foundation model for pedestrian trajectory forecasting via
federated training. A server positioned at the edge of the cellular network is responsible for aggregating the local model's parameters from the vehicles and updating the global model's parameters. To reduce
radio resource utilization, Low-Rank Adaptation is proposed; to decrease both the number and the size of updates, an increase in the number of training rounds performed by the vehicles per communication round is put forth. A novel figure of merit is then introduced to quantify the use of
radio resources dedicated to Vehicle-to-Infrastructure communications as required by the
federated solution. The proposed scheme delivers excellent prediction accuracy while significantly reducing the communication cost compared to alternative
federated training methods. This shows that combining fine-tuning, Low-Rank Adaptation, and a reduction of the communication periodicity between the vehicles and the edge server is key to enabling a distributed approach to trajectory prediction in vehicular environments.
Read the full abstract ▾
Data Structures and Algorithms
Subgaussian Vector Balancing by an Ising Model
Heng Guo, Daniel A. Spielman and Xinyuan Zhang
We show that the guaranties of the Gram-Schmidt Walk
Algorithm of Bansal, Dadush, Garg, and Lovett can be achieved by an Ising model. Given vectors $v_1, \ldots, v_n$ of norm less than 1, we give a closed form for a centrally symmetric distribution on a vector $\sigma \in \{\pm 1 \}^n$ so that the signed sum $\sum_j \sigma(j) v_j$ is $1$-subgaussian. We show that the Glauber dynamics for this model mix rapidly provided that the norms of the input vectors are bounded below 1 by an inverse-
polynomial. The proofs employ the theory of Lorentzian
polynomials, and we use these techniques to show fast mixing bounds for other
spin systems.
Read the full abstract ▾
Artificial Intelligence
To Align or Not To Align: Check Your COMPASS Before You Train
Fabian Gröger, Petar Damjanović and Maria Brbić
Combining pretrained models is a common strategy for building AI systems, whether by aligning a
vision encoder with a
language model or merging fine-tuned checkpoints. However, finding compatible pairs typically requires costly empirical search, as compatibility is known only after
alignment or merging. We propose COMPASS (COMPatibility ASsessment Score), a theoretically motivated diagnostic that estimates whether a model pair will be compatible prior to
alignment or merging. Building on the observation that representational convergence is most robust at the level of local neighborhoods, COMPASS decomposes model compatibility into two cheap-to-compute axes: a pair-specific ease, defined as the $k$-NN overlap between the two encoders, and a paradigm-level ceiling, capturing the maximum overlap their training paradigms allow. Together, these two axes provide a ranking of candidate model pairs and prescribe how to act on each pair: (i) prioritize pairs that already agree and whose paradigms are compatible, (ii) invest additional compute on pairs with compatible paradigms but low initial agreement, (iii) switch the pretraining paradigm when it cannot support sufficient agreement, or (iv) deprioritize pairs that score poorly on both axes. We apply COMPASS to $72$ cross-modal
alignment experiments and $392$ task-arithmetic model merges and show that compatibility estimates by COMPASS strongly correlate with downstream success, achieving average Pearson correlation of $0.91$ on cross-modal
alignment tasks and $0.70$ on model merging.
Read the full abstract ▾
Robotics
Grid or Nodes? Probing Object Memory in World Models Under Partial Observability
Justin McMillen and Yasin Yilmaz
A
robot's world model must remember objects that leave the camera's view. FloWM, a learned world model, keeps them in a spatial grid of features that it moves with five built-in velocities. A node
memory instead keeps each object's position and velocity as numbers. We compare them in FloWM's own block world, with an oracle-fed Kalman tracker as the node
memory. How the grid is read changes its score: a single-
cell probe finds 66% of out-of-view blocks, while FloWM's own probe 89%. FloWM also scores 8 points higher in view although no frame is shown, which we attribute to its write-back of its own predictions. Out of view, the tracker reaches FloWM's range in 14KB against 5.6MB, with no probe. On diagonal motion, outside its five velocities, FloWM finds 11% of blocks even after fine-tuning, while the unchanged tracker keeps 93%. Faster blocks defeat both until one more allowed speed takes the tracker to 94%, where FloWM's built-in shifts would need 25 copies of its grid. A learned node
memory must still replace the oracles and handle velocity under noise, long gaps, and the bounce.
Read the full abstract ▾
Software Engineering
DTScribe: Generating Models for Digital Twin Reporting using Local Large Language Models
Kérian Fiter, Angelica Portocarrero and Bentley Oakes
The development of a digital twin brings together many stakeholders and technical components. We have previously investigated the reporting of the conceptual architecture for these digital twins as an artifact for discussion. However, we find that the activity of modeling the digital twin for visualization and consensus-building can be quite tedious and time-consuming. In this article, we explore the automation of model generation using large
language models, targeting the model required for digital twin reporting. Our approach is designed to ingest digital twin documents and output both the conceptual architecture visualization and a reporting page for that digital twin. We first extract from the input the key details aligning with our twenty-one-characteristic Digital Twin Description Framework described in previous work. Then, we generate a description model in the Ontological Modeling
Language, representing the digital twin as a constellation of models, data, enablers, and services. We utilize refinement loops with large
language models acting as judges and ontological
reasoning to increase artifact quality as measured by our metrics. We investigate how architectural and parameter choices affect artifact quality, such as how refinement loops enable local large
language models to produce sufficiently high-quality results comparable to larger models. We also detail insights and lessons learned useful for practitioners, such that they can integrate our techniques to accelerate their digital twin reporting or for other model generation tasks. These insights include the use of medium-sized local models (around 20 billion parameters), the avoidance of large
language models as judges and clustering for characteristic extraction, and the recommendation of at least two reasoner loops for Ontological Modeling
Language refinement.
Read the full abstract ▾
Machine Learning
Geometric Calibration of Supervised Fine-Tuning
Jianzhu Bao, Jia-Chen Gu, Qingyuan Liu et al. (+4 more)
Recent studies investigate the weight geometry through its spectral structure, which characterizes how the weights transform different input directions. Within this view, supervised fine-tuning (SFT) is shown to induce dense updates that perturb the spectral geometry of pre-SFT weights along their principal directions, potentially disrupting the model's prior knowledge. These observations motivate using the geometry of pre-SFT weights as a reference for refining learned SFT updates. We study this perspective as
Geometric Calibration and develop SPACE Subspace Projection for Adapted Checkpoint Enhancement), a lightweight post-hoc method that selectively reverts SFT update components within the principal subspace of the pre-SFT weights while preserving those in its orthogonal complement. SPACE is a data-free, training-free method that requires only the pre- and post-SFT checkpoints. We evaluate SPACE on Qwen2.5, Qwen3, Qwen3.5, Llama-3.1, and Olmo-3 models ranging from 2B to 14B, across mathematical, coding, and medical SFT, as well as several SFT variants. Overall, SPACE mitigates out-of-domain (OOD) capability regression while further improving in-domain (ID) performance over the uncalibrated SFT checkpoints. For math SFT, SPACE yields average ID/OOD gains of 2.85/2.26 points on Qwen2.5-7B, and 2.41/1.52 points on Qwen3-14B-Base, respectively. These results highlight how the
geometric relationship between SFT updates and pre-SFT weights shapes the adapted model's capabilities and, more broadly, motivate geometry-aware parameter updates for continual model improvement.
Read the full abstract ▾
All authors Jianzhu Bao, Jia-Chen Gu, Qingyuan Liu, Haozhen Zhang, Kai-Wei Chang, Nanyun Peng, Wenya Wang
Information Theory
Solomonoff induction of selected bits and online classification
Bruno Bauwens and German Kuznetsov
Solomonoff induction is a general solution for sequence prediction that started the field of algorithmic information theory around 1960. Let $M$ be the universal semimeasure. After observing a string $\omega_1 \cdots \omega_{n-1}$, it predicts the next bit $\omega_n$ to be $b$ with conditional probability proportional to $M(\omega_1 \cdots \omega_{n-1} b)$. Thus the error of this probability is \[ e_\omega(n) = 1 - \frac {M(\omega_1 \cdots \omega_{n-1}\omega_n)} {M(\omega_1 \cdots \omega_{n-1} 0) + M(\omega_{1} \cdots \omega_{n-1} 1)}. \] If $\omega$ a computable infinite sequence with a self-delimiting description of at most $k$ bits, then $\sum_n e_\omega(n) \le k\ln 2+O(1)$. Lattimore, Hutter and Gavane consider the problem of predicting computable patterns in a sequence, for example, the pattern of repeated bits $\omega = 00\,11\,00\,00\,11\,00\cdots$ They show that the error probabilities of the bits fixed by a computable pattern have limit zero, for example, for repeated bits, one has $\lim_n e_\omega(2n) = 0$. We show that for some computable pattern, the sum of $e_{\omega}(n)$ over positions $n$ from the pattern is not bounded. However, the sum of squares $(e_\omega(n))^2$ is bounded exponentially in the program length of the pattern. It is also shown that bits of $\omega$ that are fixed by a computable classification function $f:\{0,1\}^* \rightarrow \{0,1\}$, converges faster: the sum of $(e_\omega(n))^2$ is bounded by a
polynomial in the program length for programs whose runtime is bounded by any fixed computable time bound.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Dynamic Programming for A Linear-Gaussian Dual Control Problem
Ying Wang, Yuchao Li and Håkan Hjalmarsson
We consider an infinite-horizon discounted dynamic programming (DP) problem for a countable-innovation belief-state model. The model is a surrogate for a linear-Gaussian dual control problem involving an unknown parameter vector and Gaussian observation noise. The surrogate preserves the first two moments of the Gaussian innovation and the resulting posterior second-moment structure. We allow unbounded belief and control spaces and nonnegative stage costs with quadratic growth in the posterior mean and covariance. Using a posterior-moment weight, we show that the Bellman operator is a contraction in a weighted sup-norm space. We characterize the optimal cost as the unique solution of the Bellman equation in this space, establish the existence of optimal stationary policies. We further prove weighted sup-norm convergence of value iteration, policy iteration, and optimistic policy iteration under vanishing approximation errors. The convergence results under vanishing approximation errors rely on general weighted sup-norm contraction properties and are applicable beyond the particular dual control problem considered here.
Read the full abstract ▾
Computation and Language
Breakdown of Conversational Involvement: A Joint Multi-Modal Analysis of Conversation Floors and F-formation Detection with Multiple Features
Zonghuan Li, Chirag Raman and Hayley Hung
Interactions happen universally and spontaneously in daily lives. Studying involvement in interactions helps us analyze who can influence who and has a wide potential in applications. Specifically, we consider conversational involvement in free-standing conversations. We study two operationalizations of an FCG: F-formations and conversation floors, and propose that current assumption that F-formations capture single conversations is insufficient. To illustrate how different implementations could impact the detected F-formations, we employ three analyses. First, we propose that speaking status can be used for estimating conversation floors, and leveraged it to analyze floors within F-formations. Second, we analyze spatial characteristics of the detection results by applying different feature sets on chosen baselines, and find that groups resulting from head features are more likely to be subsumed by groups detected using other features. Finally, we do a joint analysis which combines the spatial features and floor patterns in the conversation. We observe that certain pipelines can detect groups with single floors from upper body features, while retaining F-formations with lower body features. We conclude that a more detailed theory and framework is needed to holistically demonstrate conversational involvement within interactions.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from econ.TH
Falsification-proof non-market allocation mechanisms
Eduardo Perez-Richet and Vasiliki Skreta
Relying on manipulable characteristics to target the allocation of resources is fraught with difficulties. Naively optimal rules lead to falsification and allocative inefficiency. Optimizing the rule for allocative efficiency while accounting for falsification typically induces falsification, at a heavy cost to the
agents. Moreover, falsification generates negative externalities. We characterize optimal falsification-proof rules under a broad range of falsification technologies. We also provide an honesty condition under which they solve the unconstrained problem of a planner who maximizes a weighted sum of allocative surplus and
agents' welfare.
Read the full abstract ▾
Computer Vision
MajorTOM:Elliot Pretrain, A Multi-Sensor, Multi-Temporal Pretraining Dataset for Earth Observation
Carmen Oliver Huidobro, Mikolaj Czerkawski, Kevin Monsalvez-Pozo et al. (+3 more)
Pretraining generalist Earth observation foundation models requires data that combine several sensors, varied temporal sampling and, increasingly, text, yet open
datasets rarely provide all three in one consistent, easily accessible form. We introduce MajorTOM:Elliot Pretrain, a collection of 279,166 tiles of 10 km drawn from the Major-TOM grid by clustering AlphaEarth
embeddings. Each tile stacks Sentinel-2 L1C, Landsat-8/9, Sentinel-1 RTC, Copernicus DEM and ESA WorldCover on a shared 1056x1056-pixel, 10 m grid, complemented by cloud masks, OpenStreetMap entities and ERA5 weather. The tiles are partitioned into three temporal regimes, Monotemporal (250,000 tiles, one acquisition), Monthly (12,500 tiles, twelve acquisitions spread over the annual cycle) and Burst (16,666 tiles, six acquisitions within 30 days), and are released as 6.3 TB of Cloud Optimized GeoTIFFs indexed by TACO v3 Parquet metadata, a standard that allows cloud streaming, efficient data access, and filtering before any pixel is read. A companion library derives sensor-tagged fact sheets, captions and 16 families of
vision-
language tasks from these layers at load time. We test our design choices in short pretraining runs of OlmoEarth-Base. First, a 25% subset of Major-TOM Core-S2L2A curated with AlphaEarth
embeddings matches or exceeds the full corpus on 8 of 9
benchmarks. Second, on Elliot-Pretrain, adding Landsat-8/9 improves or matches Sentinel-2 only pretraining on every
benchmark. Third, using DEM and WorldCover as prediction targets during pretraining further improves 8 of 9
benchmarks, while giving the same maps to the encoder as inputs degrades 5 of 9. Fourth, Sentinel-1 helps on 7 of 9
benchmarks, particularly on
benchmarks with radar inputs. Fifth, rule-based captions match a small
language model at no cost. The
dataset is openly available at https://source.coop/major-tom/elliot-pretrain.
Read the full abstract ▾
All authors Carmen Oliver Huidobro, Mikolaj Czerkawski, Kevin Monsalvez-Pozo, Cesar Aybar, Gustau Camps-Valls, Oscar J. Pellicer-Valero
Machine Learning · Cross-listed from math.ST
Minimax rates for pointwise CATE estimation: the role of design smoothness
Yuxuan Hou and Zhenghan Li
We study the role of design smoothness in the minimax estimation of conditional average treatment effects at a fixed
covariate point. For design densities bounded above and away from zero, without further regularity, we derive upper and lower risk bounds with an arbitrarily small gap in the convergence-rate exponent. Under uniform design, we obtain matching upper and lower bounds at interior points in the regime of low nuisance smoothness. These results show that rough
covariate designs can lead to slower rates than uniform designs, even under the same smoothness assumptions on the treatment effect and nuisance functions, highlighting the role of the
covariate distribution in pointwise causal estimation.
Read the full abstract ▾
Information Retrieval
Structural Segmentation for Brazilian Legal Document Retrieval
Leandro Carísio Fernandes, João Alberto de Oliveira Lima, Hudson de Martim et al. (+3 more)
Long legal documents are often represented as single
retrieval units, which can dilute relevant content and limit
retrieval effectiveness. This study investigates structural segmentation as a document representation strategy to improve Brazilian legal document
retrieval. Using the hierarchical structure of legal acts, we represent each document as a collection of chunks. We evaluate four representation strategies: a multi-layered hierarchy representation and three simplified versions based on core chunks (articles and non-normative document components), with varying contextual details. We test these strategies on two publicly available Brazilian legal
datasets containing normative acts and legislative proposals, using both lexical and dense
retrieval models. Results show that structural segmentation improves dense
retrieval compared with whole-document indexing, despite substantially increasing the number of indexed units. However, it does not consistently benefit lexical
retrieval. Finally, we find that full hierarchicy representation is not necessary: core chunks enriched with document metadata yield comparable or better results.
Read the full abstract ▾
All authors Leandro Carísio Fernandes, João Alberto de Oliveira Lima, Hudson de Martim, Eduardo Seiti de Oliveira, Roberto Lotufo, Jayr Pereira