Robotics
Mixed-Reality Feedback Control: Towards Blending of Control and Digital Twinning
Melisa Soydan and Mario Gleirscher
Technologies, such as co-simulation, in particular, digital twins (DTs) are used for comprehensive and reliable prototyping, verification and validation (V&V) of control systems. There, the combination of feedback loops across multiple realities (e.g., simulations, physical setups) enables various forms of experimentation with
robots and autonomous systems. However, the handling of multiple realities requires a more specific support by the modelling techniques used in control engineering. To streamline the latter in the system life cycle, we propose a framework for mixing (i.e., fusing, defusing) control input and feedback signals (i.e., stimuli, responses) in simultaneously operated plants for multiple realities.
Read the full abstract ▾
Computation and Language
Qwen-MT-Lumen at WMT2026: Instruction-Specialized Translation via Quality-Aware Training and On-Policy Distillation
Hao Wang, Yangyang Liu, Xiaohu Zhao et al. (+11 more)
We present Lumen, The open-source model is available at, our submission to the WMT 2026 General Machine Translation Shared Task. We focus on instruction-specialized translation, where systems must produce accurate translations while satisfying fine-grained requirements on style, terminology, and structured output. Lumen follows a four-stage pipeline. First, continued pre-training and supervised fine-tuning jointly strengthen multilingual translation competence and the ability to follow translation-specific instructions, such as terminology, style, and format constraints. Second, we extend the originally offline M^{2}PO preference-optimization framework into an online preference-optimization stage: the current policy samples candidate translations, an LLM judge assigns continuous direct-assessment scores, and the resulting multi-pair preferences are used to update the model. Third, on-policy
distillation transfers stronger translation-instruction-following behavior from a larger teacher model to the Qwen3-14B student, improving translation-instruction adherence while retaining a 14B primary translation backbone. Finally, structure-aware inference and postprocessing preserve required formats, while selective repair addresses clear structural or decoding failures before submission. We participate in 23 translation directions. Under an absolute 1–5 LLM-judge rubric that evaluates translation-instruction following and translation quality separately, Lumen reaches an overall mean score of 4.60. Despite using a 14B translation backbone, it achieves performance comparable to leading proprietary systems in both translation quality and translation-instruction following.
Read the full abstract ▾
All authors Hao Wang, Yangyang Liu, Xiaohu Zhao, Heng Liu, Zifu Shang, Tianhao Li, Ruize Gao, Jialong Tang, Liangying Shao, Haoran Wei, Baosong Yang, Linlong Xu, Longyue Wang, Weihua Luo
Systems and Control
Iteratively Convex Frequency Data-Driven Synthesis of Structured MIMO Controllers
Luuk Marceau Spin, Thom Samuels, Dragan Kostic et al. (+3 more)
Frequency-response-function-based controller design enables synthesis directly from measured data, avoiding the need for accurate parametric plant models. This paper presents a generalized IQC-based approach for convex synthesis of structured
MIMO feedback and feedforward controllers from frequency response function data. The framework supports flexible controller parametrizations, multiple performance objectives, and both singular-value and element-wise performance shaping of
MIMO controllers within a unified frequency-domain formulation. To facilitate practical deployment, the synthesis approach is embedded within a bootstrapped controller design methodology that progressively increases controller flexibility while refining the performance specifications. The resulting approach is validated experimentally on the motion stage of an industrial wirebonder, where clear performance improvement is demonstrated through
MIMO $\mathcal{H}_\infty$ synthesis, element-wise feedback shaping, and dynamic feedforward design. The results demonstrate that high-performance multivariable controllers can be synthesized directly from measured FRF data in a practical and systematic manner.
Read the full abstract ▾
All authors Luuk Marceau Spin, Thom Samuels, Dragan Kostic, Maurice W. P. M. H. Heemels, Nathan van de Wouw, Roland Toth
Computation and Language
Beyond Reachability: A Relation-Semantic Reasoning Framework for Biomedical Multi-hop QA
Ziyang Ling, Ziyi Chen, Ronald X.Xu et al. (+1 more)
Biomedical multi-hop
reasoning over knowledge graphs requires identifying a semantically valid relation sequence that supports the answer. Existing methods can retrieve correct answers, yet often rank them poorly within a large pool of seemingly relevant candidates. Even when a correct answer is retrieved, its associated evidence and
reasoning path may fail to support the relation composition required by the question. We term this disconnect between answer reachability and evidential validity the reachable-but-invalid problem. We present ReSemReason, which shares a question-induced distribution over typed, directed relation schemas between candidate discovery and evidence selection. Schema compatibility guides graph search; ReSemAttn then uses relation-conditioned key/value projections and an uncertainty-weighted path prior to attend to candidate-specific evidence. A separate absolute-support score complements normalized
attention when all retrieved paths are weak. The reported experiments on BioHopR, PrimeKGQA, and MedReason show improvements in answer ranking and answer-set quality. Path-discrimination analyses examine the distinction between endpoint correctness and evidential support. We also specify matched controls for search,
attention, and schema uncertainty.
Read the full abstract ▾
All authors Ziyang Ling, Ziyi Chen, Ronald X.Xu, Mingzhai Sun
Robotics
Coordi-pi: Coordination-Aware Dual-Hand Action Representation for Bimanual Dexterous Manipulation
Yiming Meng, Yanming Shao, Weijie Shen et al. (+4 more)
Vision-
language-action (VLA) models have shown strong potential for general-purpose robotic manipulation, but extending them to bimanual dexterous manipulation introduces a high-dimensional and structured action space. Existing bimanual VLA policies commonly concatenate right- and left-side arm–hand actions at each control timestep, leaving cross-hand interactions implicit within a single action vector. We introduce Coordi-$\pi$, a structured action representation for bimanual dexterous manipulation. Coordi-$\pi$ represents the right- and left-side arm–hand actions as individual action
tokens and organizes them into an interleaved sequence, explicitly exposing the two sides within the action sequence. To explicitly encode hand identity and temporal synchronization in this interleaved representation, a learnable hand-identity
embedding distinguishes the two sides, while sequence–control-timestep factorized rotary positional encoding (RoPE) separates sequence position from control timestep, allowing actions at the same control timestep to share a temporal coordinate while retaining distinct sequence positions. Across all five bimanual dexterous manipulation tasks in DexJoCo, Coordi-$\pi$ achieves state-of-the-art performance under both rand-obj and rand-full, improving the average success rate over $\pi_{0.5}$ from 31.9% to 51.3% and from 18.3% to 32.3%, respectively. Coordi-$\pi$ also consistently outperforms $\pi_{0.5}$ across four real-world bimanual dexterous manipulation tasks.
Read the full abstract ▾
All authors Yiming Meng, Yanming Shao, Weijie Shen, Kunyang Lin, Jiayu Sun, Ping Luo, Yao Mu
Systems and Control
Severity-Aware Minimum Security Sets for Accelerated Preventive SCOPF Using Machine Learning
Mohammad Iman Alizadeh, Saeed Zeynali, Salah Ghamizi et al. (+1 more)
This paper proposes a severity-aware machine learning framework for reducing the computational burden of preventive AC security-constrained optimal power flow (PSCOPF). The central idea is to identify a compact minimum security set (MSS) containing only the non-dominated contingencies and associated post-contingency constraints that materially influence the preventive operating point while satisfying a prescribed severity tolerance. An offline procedure combines AC security assessment, severity-based ranking, non-dominated screening, and iterative reduced PSCOPF. After each reduced PSCOPF solution, exhaustive security assessment over all credible contingencies identifies additional contingency–constraint pairs whose residual severity exceeds the specified threshold. Severity is characterized using the normalized number, accumulated magnitude, maximum magnitude, and average magnitude of post-contingency violations. The resulting operating-point-dependent MSSs are used as labels for a supervised multi-label learning model that predicts the security elements required to construct the reduced PSCOPF directly from the pre-contingency state. The proposed framework therefore focuses the optimization on the contingencies and constraints that affect preventive control decisions, reducing problem size and computation time while explicitly controlling residual post-contingency severity. Results on the IEEE 60-bus and 118-bus systems, the latter having an approximately seven-times-larger PSCOPF formulation, demonstrate substantial computational reductions with limited impact on the preventive operating solution.
Read the full abstract ▾
All authors Mohammad Iman Alizadeh, Saeed Zeynali, Salah Ghamizi, Sylvain Kubler
Numerical Analysis
Finite Volume Methods
Robert Eymard, Thierry Gallouët and Raphaèle Herbin
This chapter focuses on finite volume methods. The finite volume method is a discretization method that is well suited for the numerical simulation of various types (for instance, elliptic, parabolic, or
hyperbolic) of conservation laws; it has been extensively used in several engineering fields, such as fluid mechanics, heat and mass transfer, or petroleum engineering. Some of the important features of the finite volume method are similar to those of the finite element method: it may be used on arbitrary geometries, using structured or unstructured meshes, and it leads to robust schemes. The finite volume method is locally conservative because it is based on a “balance” approach: a local balance is written on each discretization
cell that is often called “control volume;” by the divergence formula, an integral formulation of the fluxes over the boundary of the control volume is then obtained. The fluxes on the boundary are discretized with respect to the discrete unknowns.
Read the full abstract ▾
Robotics
One-shot Human Video-Guided Adaptation for Vision-Language-Action Models
Qi Chen, Yuwei Wu, Quan Chen et al. (+5 more)
Vision-
language-action (VLA) models have recently achieved remarkable progress by leveraging large-scale
robot datasets and foundation models for general-purpose
robot manipulation. However, their ability to rapidly adapt to novel manipulation tasks beyond the training distribution remains limited. Existing approaches often require task-specific
robot demonstrations and additional training, which are labor- and compute-intensive, limiting the scalability of VLA adaptation to open-world scenarios. To reduce this dependence on target-task
robot data, we propose CapPro, a framework that enables a VLA policy to adapt to previously unseen manipulation tasks using only a single human demonstration
video. CapPro consists of two components. First, a phase-aware human
video representation module constructs a compact
video representation through learned visual
token selection and learns task-relevant query representations under phase-caption supervision. Second, a
video-conditioned adaptation module jointly incorporates the compact
video and query-derived representations into the action-conditioning context of the pretrained VLA policy. % This design introduces task-specific guidance while largely preserving the original VLA action-generation backbone. In this way, the human demonstration provides task-specific execution guidance rather than an embodiment-aligned trajectory to imitate, without requiring target-task
robot demonstrations or target-task fine-tuning. Experiments across source and unseen target tasks show that CapPro improves average performance across unseen target groups while maintaining comparable performance on the source tasks. These results demonstrate the effectiveness of human-
video guidance for cross-task VLA adaptation.
Read the full abstract ▾
All authors Qi Chen, Yuwei Wu, Quan Chen, Kunpeng Gao, Jin Chen, Che Sun, Zhi Gao, Yunde Jia
Computer Vision
Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors
Junhoo Lee, Hyeonjin Kim, Sangbum Han et al. (+1 more)
Discriminative models are trained with task-specific objectives such as classification, detection, or representation learning, yet their practical utility depends on generalizing beyond the training task to unseen samples from the same domain. This suggests that a discriminative model may retain an implicit trace of the data
manifold beyond its task labels. We ask whether this trace can be exposed as a generative signal without task-specific guidance. We introduce the Discriminative Score Function (DSF), which extracts an image-space generative field from the loss-gradient geometry of a pretrained discriminative model. DSF provides a training-free update rule that moves images toward model-consistent visual regions without retraining or task-specific targets. We apply DSF to diverse pretrained discriminative models, including ResNet classifiers, DETR detectors, and DINOv2 ViT encoders. DSF generates unconditional images from noise and supports conditional guidance, editing, inpainting, and explanation through the same field. DSF-generated samples also provide effective zero-shot quantization calibration when real images or labels are unavailable, preserving feature geometry better than data-free calibration baselines. These results show that discriminative training leaves a generative functional signal for synthesis and calibration. Project page: https://junhoo.me/dsf.
Read the full abstract ▾
All authors Junhoo Lee, Hyeonjin Kim, Sangbum Han, Nojun Kwak
Computer Vision
HyperLoop: Hyperspectral-Assisted Loop Closure Detection in 3D-SLAM for Planetary Exploration
Annie Bhalla, Dennis Rotondi, Riccardo Giubilato et al. (+2 more)
Autonomous navigation of planetary rovers is challenged by visually repetitive, featureless terrain. SLAM systems based on 3D Gaussian Splatting (3DGS) offer dense mapping but rely on RGB appearance descriptors that degrade under perceptual aliasing - a common failure mode in extraterrestrial environments where physically distinct locations appear visually identical. This paper presents HyperLoop, the first framework integrating hyperspectral imaging (HSI) into the loop closure module of a 3DGS-based SLAM system. Hyperspectral descriptors encode material-level spectral signatures complementing RGB features, providing robustness to illumination changes and visual repetitiveness. Two HSI descriptor families are introduced: Bag-of-Spectral-Words (BoSW), encoding spectral material distributions via TF-IDF weighted histograms, and PCA-K VLAD (PCAK-VLAD), capturing first-order residual statistics of PCA-compressed spectral signatures. Both are evaluated with SIFT-VLAD and NetVLAD RGB descriptors under Strict-AND and Weighted fusion strategies on a custom
dataset from the Moon-Mars Outdoor Test Site (MMOTS) at DLR, comprising synchronized RGB-D and hyperspectral sequences across four planetary analog traverses (65.5 m total). A key finding is that the sensor's Red-NIR range (600-860 nm) provides limited discriminability for rock terrain: the best HSI fusion (SIFT-VLAD + BoSW, Strict-AND) achieves 5.04 cm ATE RMSE, within 1.8% of SIFT-VLAD alone (4.95 cm). The gain over NetVLAD (8.81 cm) is attributable to SIFT-VLAD, not HSI fusion. This motivates future adoption of SWIR sensors capturing diagnostic mineral absorption features absent from the 600-860 nm range for planetary SLAM missions.
Read the full abstract ▾
All authors Annie Bhalla, Dennis Rotondi, Riccardo Giubilato, Kai O. Arras, Wolfgang Stuerzl
Computation and Language
Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs
Minghan Li and Guodong Zhou
Visible
reasoning traces of Chinese
reasoning-oriented LLMs are typically written in modern vernacular Chinese, which may be verbose under limited decoding budgets. We ask whether the linguistic register of
reasoning can be used to improve efficiency. We propose Wenyan Thinking, which emits intermediate
reasoning in Classical Chinese (wenyanwen) while retaining a short direct-answer output. Starting from modern-Chinese
reasoning traces, we rewrite only the
reasoning field into wenyan and fine-tune Qwen3-4B-Thinking-2507 on the rewritten supervision. To distinguish register shift from generic compression, we construct a compact modern-Chinese control using the same source data, teacher family, base model, and SFT recipe. Across budget-sensitive evaluations on MMLU-ProX-Lite-ZH, CEVAL, and AGIEval-CN, Wenyan Thinking substantially reduces
reasoning length and missing-answer rates under constrained decoding. Compact rewriting explains much of the efficiency gain, while wenyan consistently outperforms the compact modern-Chinese control on the primary
benchmark and remains competitive across the additional
benchmarks. These results identify linguistic register as a practical design axis for efficient visible
reasoning in Chinese LLMs.
Read the full abstract ▾
Machine Learning
ProtModernBERT: Compute-Efficient Protein Language Modeling
Alberto Martínez, Natalia Flechas Manrique, Llorenç Espinosa-Portalés et al. (+1 more)
Large
protein language models provide a powerful framework for learning sequence-function relationships and guiding experimental design. However, architectural improvements are underexplored, especially in low-compute regimes of relevance for resource-constrained research laboratories. We show that the training cost for encoder-only
transformer architectures can be reduced by leveraging modern architectural refinements, offering an encouraging performance / compute-efficiency trade-off. We introduce ProtModernBERT, a modernized BERT-style model pre-trained on amino acid sequences, and compare it with ProtBert, Amplify, and ESM2 across a set of supervised structural tasks -encompassing secondary structure prediction, disorder prediction, and subcellular localization- and ProteinGym's zero-shot functional
benchmark. We find that ProtModernBERT matches or closely tracks the performance of Amplify-120M and ProtBert with up to 80-90% reduction in pre-training FLOPs, and narrows the gap to ESM2 when controlling for pre-training. Our analysis using a cluster-based validation protocol for hyperparameter selection and randomly initialized models disentangles the contributions of architecture and data, showing that modern components provide stronger inductive biases that are more consequential than parameter count in low-compute regimes.
Read the full abstract ▾
All authors Alberto Martínez, Natalia Flechas Manrique, Llorenç Espinosa-Portalés, Luc Andrea
Computation and Language
MakSafe: A Spatiotemporal Semantic Framework for Formal Specification and Compliance Checking of Road Vehicle Safety Rules
Maksym Labzhaniia, Julien Deantoni, Marie-Agnès Peraldi-Frati et al. (+1 more)
Scenario-based validation is essential for automated road vehicles but cannot cover the full variability of openworld traffic. We present MakSafe, a formal spatiotemporal framework for specifying and checking road vehicle safety rules through semantic zones, action-based forecasting, and trace-tree
reasoning, avoiding uniform time discretization. We formalize the road network, vehicle states, and occupancy zones, then build executable rules for front-vehicle identification and timeto-collision (TTC) verification. The evaluation combines a tracedependent case study with a scalability
benchmark over traffic density (N ), horizon (H), and branch factor (B). MakSafe yields branch-specific verdicts, deriving safe and unsafe outcomes from the same initial scene, and re-evaluates a scenario after a control update. A single rule check stays well below a millisecond across the reported sweep, and longer horizons slow the TTC check.
Read the full abstract ▾
All authors Maksym Labzhaniia, Julien Deantoni, Marie-Agnès Peraldi-Frati, Frédéric Mallet
Computer Vision
Object Pose from 2-D to 3-D Point and Line Correspondences
Thai Quynh Phong, Radu Horaud, Adnan Yassine et al. (+1 more)
In this paper we present a method for optimally estimating the rotation and translation between a camera and a 3-D object from point and/or line correspondences. First we devise an error function and second we show how to minimize this error function. The quadratic nature of this function is made possible by representing rotation and translation with a dual number quaternion. We provide a detailed account of the computational aspects of a trust-region optimization method. This method compares favourably with Newton's method which has extensively been used to solve the problem at hand, with Faugeras-Toscani linear method [6] for calibrating a camera, and with the Levenberg-Marquardt non-linear optimization method. Finally we present some experimental results which demonstrate the robustness of our method with respect to image noise and matching errors.
Read the full abstract ▾
All authors Thai Quynh Phong, Radu Horaud, Adnan Yassine, Pham Dinh Tao
Multiagent Systems
Exact Cut Complexity of Equal-Length Proportional Cake Cutting
Yasushi Kawase, Bodhayan Roy and Mohammad Azharuddin Sanpui
We study proportional cake cutting under an equal-length constraint, where each of $n$
agents must receive a bundle of length exactly $1/n$ that is worth at least $1/n$ to that
agent. Our main result determines the exact worst-case number of cuts needed to guarantee such an allocation, namely $2n-2$ for every $n$. This improves on the previously known quadratic upper bound. The proof combines the constrained necklace-splitting
theorem with a recursive assignment argument based on Hall's
theorem. The same bound extends to the stronger requirement of envy-freeness when $n$ is a
prime power, and an $O(n^{1.525})$ upper bound holds for arbitrary $n$. We then ask whether such allocations can be computed. We first show that no deterministic protocol in the Robertson–Webb model terminates after finitely many queries on every instance and always returns an exact equal-length proportional allocation, even for two
agents with identical valuations. For every $\varepsilon>0$, however, $O(n^2/\varepsilon)$ queries suffice to produce an allocation in which every
agent receives a bundle of length exactly $1/n$ and value at least $1/n-\varepsilon$, again using at most $2n-2$ cuts. Finally, we augment the Robertson–Webb model with two-knife queries. We show that recursive balanced halving attains the optimal bound of $2n-2$ cuts when $n$ is a power of two. For arbitrary $n$, we give a procedure using $O(n\log n)$ cuts.
Read the full abstract ▾
Neural and Evolutionary Computing
Controlling the latency in temporal coded spiking models for neuromorphic datasets
Alban Gattepaille and Alexandre Muzy
Exploiting temporal information in
datasets with high temporal dependencies (such as spoken keyword recognition) by spiking models is still an open problem. Promising frameworks include Time-To-First coding (TTFS) and the inclusion of synaptic delays into learning. In TTFS,
neurons are forced to spike at most once, forcing the network to found its learning on the spiking times of
neurons rather than their spiking rate. Some models use the TTFS framework to directly compute the spiking time of Integrate-and-Fire (IF) or Leaky Integrate-and-Fire (LIF)
neurons. However, most models built in the TTFS framework have not been tested against
datasets containing temporal information. Little is known about the latency of these models on temporal
datasets, where the latency is the time taken by the network to correctly classify a sample. In this work, we study the behaviour of Delay Neural Networks (DeNN) models, i.e. models that directly compute the spiking time of
neurons by bypassing the membrane potential and thresholding mechanisms of spiking
neurons. We show how to analytically control their latency, and empirically study the latency-accuracy tradeoff in a dynamic temporal
dataset.
Read the full abstract ▾
Machine Learning
What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization
Julia Barth, Armin Sommer, Kunvar Thaman et al. (+1 more)
Goal misgeneralization is a common failure mode in which an
agent behaves competently out of distribution but does not pursue the intended goal. However, we still have a weak understanding of what happens to the intended goal in misgeneralizing
agents. Across three Procgen environments and five
robot tasks, we find three distinct forms of policy-goal misalignment: (1) functional target substitution, where behavior follows an alternative goal, (2) a policy shortcut, where behavior follows a learned action strategy, and (3) cue competition between intended and proxy goal cues. We distinguish these regimes by tracing where goal information remains available internally, how strongly it influences the policy, and what role it plays in action selection, and find that the goal is lost at different depths. Where the goal reaches the decision, as in cue competition, steering redirects the policy to the goal's location, raising intended-goal reach from 16.0% to 95.3%. Where it reaches the policy but not the decision, only new downstream wiring recovers goal reach, from 31.6% to 84.3% in the environment with the action shortcut. Where it is inert, neither works. Our results show that goal misgeneralization is not a single failure of goal representation, but distinct failures of policy
alignment at different depths, tightly connected to which recovery works.
Read the full abstract ▾
All authors Julia Barth, Armin Sommer, Kunvar Thaman, Jannik Schilling
Neural and Evolutionary Computing
Design and Analysis of Temporal Representations in Neural Networks
Alban Colas-Gattepaille and Alexandre Muzy
The ability to represent temporal information is often hypothesized to underlie the efficiency and learning capabilities of biological neural networks. This motivates the development of spiking neural networks. However, it remains unclear how temporal information is actually represented in neural networks and how different forms of temporal representation affect performance and computational efficiency. We introduce the notion of the degree of temporal representation of a neural network, defined by whether its constituent functions (activation, learning, encoding, and decoding) explicitly manipulate time as a computational variable. This perspective yields a continuum ranging from non-temporal representations, where time does not explicitly appear as a computational variable in the network functions, to fully temporal representations, where computations explicitly operate on temporal variables. Using a fixed deep architecture, we compare different encoding, activation mechanisms and decoding with increasing temporal expressiveness: non-temporal weighted-sum activations used in usual artificial neural networks, non-temporal binary spiking activations used in spiking neural networks, and spike-time-based activations used in delay neural networks. Experiments on event-based
datasets show that increasing the degree of temporal representation improves both performance and computational efficiency, allowing state-of-the-art performances on the Google
Speech Commands
dataset. We further analyze how temporal representations induce distinct forward and backward computational trajectories, leading to gradients that depend explicitly on the history of event times.
Read the full abstract ▾
Computer Vision
A Diagnostic Study of World-Space Human Recovery Under High Camera Dynamics
Hao-Jen Chien, Wei-Lun Chao and Yu-Lun Liu
Monocular world-space human recovery methods excel on current
benchmarks, but these rarely include fast camera motion. We introduce the K-Pop stress test, broadcast dance
videos that combine fast, large camera motion with dense multi-person choreography. Leading methods produce plausible per-frame meshes on these
videos, yet their world-space trajectories drift far from the performers' stage positions. Through a systematic diagnosis, we show that the camera and human estimates each remain self-consistent, and that the drift appears when they are combined at mismatched scales. Each is recovered at its own scale, so a mismatch between the two can turn camera motion into human drift that grows with camera displacement and becomes severe in broadcast dance
videos. We derive a closed-form correction that estimates this mismatch and applies one scale to all performers, removing the drift while keeping their relative positions in one shared world frame. It requires no retraining and works with existing backends. Combined with physical constraints, the correction yields stable world-space reconstruction for choreography modeling, scene editing, data generation, and virtual reshooting. Project page: https://chien90190.github.io/worldhmr-fastcam-website/
Read the full abstract ▾
Computer Vision
Zhixin Cai, Ruoqi Yuan, Xinchen Yang et al. (+4 more)
Video large
language models (
Video LLMs) often generate responses unsupported by the input
video. Contrastive decoding (CD) can mitigate these
hallucinations, but its effectiveness depends on how the negative branch weakens visual evidence. Existing methods rely on predefined perturbations or masking guided by question reconstruction, offering limited control over the model's visual reliance during answer generation. We introduce
Attention-guided Representation Perturbation for Contrastive Decoding (ARP-CD), a training-free framework for constructing contrastive negatives directly in representation space. ARP-CD uses the
attention mass assigned to visual
tokens at the answer-prediction position to guide bounded gradient updates of the
language model's input visual hidden states. These updates reduce visual
attention and produce a negative input, whose predictions are contrasted with those of the original branch throughout generation. Experiments across four
Video LLMs and four
benchmarks show that ARP-CD outperforms representative training-free baselines in most model–
benchmark settings, reducing
hallucinations while improving general
video understanding. Further analyses show that
attention-guided perturbation directions improve negative quality and that the resulting negatives provide effective contrastive references for correcting the original predictions.
Read the full abstract ▾
All authors Zhixin Cai, Ruoqi Yuan, Xinchen Yang, Zhuofan Chen, Jun Bai, Chuantao Yin, Wenge Rong
Computer Vision
Generative World Simulation with DAO and JING
XGEN Team: Guohao Cai, Haoxuan Che, Frank Fan et al. (+15 more)
We present a Generative World Simulation framework that couples persistent shared world state with continuous first-person audiovisual generation. The framework integrates DAO, a computable world engine, and JING, an Egocentric Interactive Experience Model, to support sustained interaction for humans and
agents. DAO maintains the states of characters, objects, and spaces and their relationships, advancing the world according to interaction rules and world time while preserving the consequences of past actions. From this evolving state, DAO derives observer-specific conditions for JING, which combines these conditions with character, object, and scene references, observation history, and current actions to generate each observer's audiovisual experience. Users can explore environments, manipulate objects, and communicate with characters through viewpoint control and text instructions, with their actions shaping both the shared state and subsequent experiences. By connecting world-state
evolution with experience generation in a continuous interaction loop, the framework offers an approach to building interactive worlds that retain their history, evolve through action, and persist beyond any individual observer.
Read the full abstract ▾
All authors XGEN Team: Guohao Cai, Haoxuan Che, Frank Fan, Chenran Huang, Junjia Huang, Jiayi Jiang, Yanheng Li, Leon Liu, Shaoteng Liu, Xi Liu, Feng Nie, Zhefan Rao, An Wang, Hanwen Wang, Pengxiang Yan, Jieming Yu, Qian Zha, Wentao Zheng
Machine Learning
TimeRSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models
Haoxin Liu, Deqing Fu, Lucheng Fu et al. (+4 more)
Time-series foundation models provide strong zero-shot forecast, but deployment for real-world applications still requires task-specific designs for model inputs and outputs. Direct inference can leave domain knowledge and recurring forecast errors unaddressed, while tailored pipelines require substantial human expertise and effort. We introduce TimeRSI, a self-improving agentic deployment system around frozen forecasting models. A coding
agent translates task descriptions into executable pipeline changes. It tests each revision on historical forecasting windows and uses observed errors to guide subsequent revisions. During deployment, an adaptive selector chooses among the resulting pipelines using completed forecasts under similar conditions. Across 198 tasks on TIME and fev-bench, TimeRSI outperforms all submissions on six point and probabilistic forecasting metrics. Controlled comparisons support the value of feedback-guided revision over non-iterative pipeline search. Further experiments verify the generalization with different coding
agents and forecasting models. Code is available at https://github.com/haoxin1998/TimeRSI.
Read the full abstract ▾
All authors Haoxin Liu, Deqing Fu, Lucheng Fu, Yiqiao Jin, Rushi Qiang, Harshavardhan Kamarthi, B. Aditya Prakash
Discrete Mathematics
Graphs with Bounded Push-Pop Walk Orderings
Antoine Amarilli, Claire David, Nadime Francis et al. (+3 more)
Consider a directed graph G and the (generally infinite) set Walks(G) of the walks in that graph. We are interested in ordering Walks(G) as w1, w2,... in a way that ensures that each walk is obtained from the previous one by a bounded number of elementary operations, namely, push operations (which add a new edge at either end of the walk) and pop operations (which remove the first or last edge of the walk). Our goal is to optimize the aforementioned bound, when it exists, in particular when imposing the additional requirement that walks must be ordered in increasing order of length. To this end, we introduce a condition on graphs inspired by earlier work, called inner-connectedness, which is testable in linear time; we show that inner-connected graphs are precisely those which admit bounded walk orderings. Focusing on such graphs, we then introduce and study the pp-rank and the pp-increasing-rank. Namely, the pp-rank of a graph is the best possible bound on the number of push-pop operations in a bounded walk ordering for that graph; and the pp-increasing-rank is the same where we further impose that shorter walks appear before longer walks in the ordering. We show that the pp-rank of inner-connected graphs is in fact always bounded by 3. The pp-increasing-rank of inner-connected graphs is also always finite, but it can be up to linear in the input graph. More precisely, we show that the pp-increasing-rank is related to a new parameter we introduce, the peripherality of graphs. In particular, for cyclic graphs, peripherality is related to the pp-increasing-rank up to multiplicative and additive constants. We last study how to compute these parameters, and show that while peripherality can be computed in
polynomial time, the pp-increasing-rank itself is generally NP-hard to compute.
Read the full abstract ▾
All authors Antoine Amarilli, Claire David, Nadime Francis, Victor Marsault, Mikaël Monet, Yann Strozecki
Computation and Language
Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding
Shun Inadumi, Lee Sangmyeong and Koichiro Yoshino
Interpreting an ambiguous utterance in real-world interactions often requires context beyond a single utterance. When the utterance refers to objects in a visual scene, it is necessary to maintain and update the set of plausible referents as context accumulates, without assuming that the available information identifies a unique object. However, prior work on interactive visual grounding, which localizes objects referred to by linguistic expressions, has focused on identifying a unique object once sufficient dialogue context becomes available. To address this gap, we propose Candidate Set Visual Grounding (CSVG), a task for estimating the set of objects consistent with the given dialogue context. We further introduce CandVG, a
benchmark that evaluates how the candidate set changes across dialogue turns. Our evaluation of
vision-
language models shows that stronger visual grounding capability does not necessarily yield better CSVG performance. In particular, models have difficulty predicting the complete candidate set, owing to challenges in candidate generation and premature commitment to a small set of candidates in early turns. Nevertheless, we find that this limitation can be partially mitigated in the evaluated large-scale models using instructions designed for CSVG.
Read the full abstract ▾
Sound
ONCship: A Large-Scale Underwater Acoustic Corpus for Ship Recognition
Zhe Cao, Jichao Zhang and Xiao-Lei Zhang
Recent advances in deep learning have significantly improved underwater acoustic vessel recognition. However, existing publicly available
datasets are typically limited in scale, hindering large-scale representation learning and downstream task evaluation. To address this limitation, we introduce ONCship, a large-scale underwater acoustic
dataset comprising 4521 hours of curated recordings from Ocean Networks Canada (ONC) hydrophones and Automatic Identification System (AIS) data. We evaluate the proposed
dataset across three tasks: self-supervised representation learning, vessel-type classification, and MMSI-Level Vessel Classification. Experiments on DeepShip and ShipsEar demonstrate the effectiveness of ONCship for acoustic representation learning, with joint pre-training on ONCship and AudioSet achieving a classification accuracy of 62.45% on DeepShip through linear probing. Furthermore, incorporating ONCship as auxiliary training data improves downstream vessel-type classification performance. Beyond conventional vessel-type classification, we further investigate MMSI-Level Vessel Classification, treating each vessel as a distinct identity. Experimental results show that models fine-tuned with different loss functions achieve Top-1 accuracies exceeding 53% and Top-5 accuracies approaching 69%, demonstrating the feasibility of distinguishing individual vessels through MMSI-Level Vessel Classification. Overall, ONCship provides a valuable resource for underwater acoustic representation learning and vessel recognition, while its rich vessel-level metadata enables further exploration of MMSI-Level Vessel Classification.
Read the full abstract ▾
Artificial Intelligence
Articulation Upper Bounds for Language Models
Alexander Spangher, Daniel E. Ho, Diyi Yang et al. (+2 more)
Language captures only a subset of the perceptions, intuitions and intents that form meaning between speakers. What, then, are the limits of
language? We take steps towards measuring this in LLMs as follows: for a set of concepts, we measure how well each concept can be transmitted between two LLMs as their capabilities scale. This requires novel measurement tools: (1) optimal messages: we introduce a
prompt optimization
algorithm that beats existing
algorithms by up to 14% on
benchmarks and accurately estimates
prompt upper bounds. (2) A transmission measure: the sender is asked to label text; the receiver then tries to recover the sender's
prompt, and recovery is measured; we find this correlates strongly with human label error. With these measures, we use observational scaling laws to study how transmissibility of a concept, conveyed with optimal messages, increases as transmitter and receiver capacity grows: does it asymptote below or above a threshold? Measuring 1.2k concepts in eight domains, we find concepts that (a) can be fully articulated; these concepts usually depend on local patterns, e.g. "joke ends with surprise"; (b) might be articulated by future, stronger models; these rely on whole-text structural patterns, e.g. "story's worldbuilding coherence"; (c) concepts that face articulability limits; these concepts' meaning, we find, is tied to identity and social-group awareness, e.g. "comic voice". Interesting, these same concepts are not all challenging for humans: humans have moderate-to-high levels of agreement in 76% of concepts that LLMs struggle with; articulation limits, we find, are executor relative. Finally, we characterize the nature of improvement in each case: while recoverable concepts can be articulated through definitions and explanations, irrecoverable concepts cannot be transmitted, even with examples, and might require novel learning mechanisms.
Read the full abstract ▾
All authors Alexander Spangher, Daniel E. Ho, Diyi Yang, Noah Goodman, Sanmi Koyejo
Artificial Intelligence
Learning Individual Scientific Taste with Privileged Hindsight Distillation
Hanwei Fan, Yanqiao Wang, Yiqi Zhu et al. (+3 more)
Scientific taste shapes which research directions researchers pursue, and it varies across individuals. Existing work evaluates research directions along multiple evaluation criteria or models scientific taste using community feedback signals such as citations and reviews, but neither directly captures how individuals translate assessments under the same criteria into different preferences. We model scientific taste as a researcher-specific mapping from criterion-level assessments in a shared, evidence-grounded evaluation space with proposal-visible evidence, to relative preferences. A population-level mapping learned from retrospective supervision provides a cold start when individual feedback is scarce. We introduce Privileged Hindsight
Distillation (PHD), which uses later-emerging scientific evidence during training to improve proposal-time criterion assessment and the population mapping, while exposing only proposal-visible information at inference. We evaluate our approach primarily in
quantum research, where structured public reviews are largely unavailable, and use pairwise proposal comparison as a direct interface for observing individual taste. With only 15 comparisons per researcher, our method captures sharply different tastes, including opposing preferences over the same research-direction pairs when they trade off across evaluation criteria. In an interactive study, personalized rankings also surface proposals associated with greater subsequent user engagement, connecting learned taste to downstream research exploration.
Read the full abstract ▾
All authors Hanwei Fan, Yanqiao Wang, Yiqi Zhu, Xuanyu Lei, Peng Li, Yang Liu
Computer Vision
No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation
Lizhi Xiong, Jun Li, Ziqiang Li et al. (+2 more)
Recent advances in
diffusion models have enabled high-fidelity, identity-preserving image generation for personalized applications such as digital avatars and virtual try-on systems. However, their reliance on sensitive facial reference images raises growing
privacy concerns. Existing defense mechanisms are primarily designed for training-based personalization and struggle to generalize to emerging training-free approaches, due to fundamental differences in their identity integration paradigms. To bridge this gap, we propose IDGuardian-the first generalizable and model-agnostic identity protection framework capable of defending against both training-based and training-free personalization methods. IDGuardian abstracts the personalization process into two critical stages: identity extraction and identity injection. It then introduces crafted
adversarial perturbations to simultaneously disrupt both stages. Specifically, it degrades the identity features extracted by external encoders and establishes an
adversarial conceptual bridge that misdirects the generative trajectory away from the target identity. Extensive experiments show that IDGuardian effectively protects identity across various personalization pipelines and model architectures, while remaining robust to post-processing, adaptive attacks, and cross-
dataset generalization. Our code is available at https://github.com/OpenAscent-L/IDGuardian.git.
Read the full abstract ▾
All authors Lizhi Xiong, Jun Li, Ziqiang Li, Weiwei Jiang, Zhangjie Fu
Sound
Soloist: A Generative Model for Blind Voice Separation in the Wild
Chen Yang, ChuFan Yu, Botian Jiang et al. (+5 more)
Real-world voice separation must recover individual voices from overlapping
speech, environmental noise, and music, yet isolated source recordings are rarely available for supervision. We introduce Soloist, a generative model for blind voice separation that autoregressively generates individual voice streams as audio-codec sequences conditioned on the mixture, without requiring a target-speaker query or a predefined voice count. We propose a two-stage training paradigm to learn from synthetic mixtures and adapt to real recordings. The first stage combines supervised separation on synthetic mixtures with isolated source targets and an auxiliary task that predicts speaker timelines from real recordings, learning who speaks when from natural acoustics. The second stage applies reinforcement learning to real recordings, with rewards supplied by a model judge that compares candidate separations based on voice purity and content preservation without isolated source targets. Across diverse scenarios, Soloist recovers clean
speech from multi-speaker overlap and noisy recordings, and extracts singing vocals from music accompaniment while maintaining relatively high pitch accuracy and intelligibility. On real-world recordings with unknown voice counts, Soloist also separates voices well. Finally, we integrate Soloist into a full-duplex conversation processing pipeline that assembles separated outputs into continuous speaker tracks, demonstrating its practical utility in real conversations.
Read the full abstract ▾
All authors Chen Yang, ChuFan Yu, Botian Jiang, Jingqi Chen, Wenxuan Wang, Yitian Gong, Zhaoye Fei, Xipeng Qiu
Information Theory
Capacity Bounds for Optical Interference Channels Subject to Average Power Constraints
Viswanathan Ramachandran
Accurate information-theoretic analysis of multiuser wavelength-division multiplexed (WDM) optical links is complicated by Kerr nonlinearity and chromatic dispersion. Existing capacity bounds for first-order regular perturbative (RP) channel models have relied on per-symbol peak power constraints to simplify the underlying extremal analysis. In this paper, we replace these peak constraints with the more practically relevant average input power constraints and study the resulting RP WDM interference channel. Unlike the peak-constrained formulation, an exact finite signal-to-noise ratio (SNR) analysis under average power leads in general to a nonconvex, high-dimensional optimization problem with no closed-form solution. We show that the problem admits a tractable characterization in the high-SNR regime. Using a genie-aided argument, we derive closed-form single-user high-SNR capacity bounds for the RP interference channel and identify constant-amplitude interferer signaling as extremal. Furthermore, under an empirically validated non-negativity condition on the dominant RP kernels and within a truncated first-order RP model, we establish a finite-SNR extremality result, yielding a single-user capacity characterization within the RP model under average power constraints. Building on these single-user corner points, we construct an all-helpsone achievable region via time sharing, which strictly improves upon treating nonlinear interference as noise. Numerical results and split-step
Fourier simulations of the nonlinear Schrodinger equation channel confirm that the qualitative conclusions persist over practical launch powers. The results provide new insight into extremal signaling and multiuser trade-offs for nonlinear WDM systems within the RP approximation.
Read the full abstract ▾