Sound
The VoiceMOS Challenge 2026: Evaluating Speech Enhancement, Emotional TTS and Accented TTS Systems
Wen-Chin Huang, Wei Wang, Marvin Sach et al. (+4 more)
We present the results of the VoiceMOS Challenge 2026, the fifth edition of a scientific challenge on automatic prediction of subjective
speech assessments. After expanding the scope to music and general audio in 2025, we refocused the evaluation target on
speech and organized three tracks: prediction of absolute and comparative category ratings for enhanced
speech, prediction of naturalness and
emotion-related tasks for emotional text-to-
speech systems, and prediction of speaker and accent similarity for codec-based
speech synthesis systems. The challenge attracted a total of 18 teams worldwide, with most teams successfully surpassing the provided baselines. We summarize the challenge results, representative top-performing systems, participant feedback, and directions for future editions.
Read the full abstract ▾
All authors Wen-Chin Huang, Wei Wang, Marvin Sach, Xiaoxue Gao, Nicholas Sanders, Erica Cooper, Toda Tomoki
Computer Vision
Restore What Matters: Lessons from Joint Restoration and Recognition
Lanqing Guo, Xijun Wang, Minchul Kim et al. (+7 more)
Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom translates to improved recognition. We propose a Joint Restoration-for-Recognition (JR$^2$) paradigm: restore only what downstream tasks truly require, with task signals dictating where, how much, and whether restoration is necessary. JR$^2$ rests on three pillars: (i) Physics, employing optics-accurate
turbulence simulation, extensible to blur and noise, to ground restoration in real image formation; (ii) Neuroscience, drawing on selective
attention and neuroplasticity to direct model capacity toward identity-critical regions and frames while bypassing already-clean inputs; and (iii)
Vision & Learning, coupling recognition loss end-to-end through restoration and
alignment so that low-level edits maximize high-level identity stability. Evaluations on IARPA-BRIAR show consistent improvements (e.g., TAR@0.01% FAR +0.6; FNIR@1% FPIR -2.5), while a quality gate skips ~70% of clean frames, reducing cost. Ablations confirm physics priors enhance realism, joint training prevents catastrophic forgetting, and selective restoration suffices in many cases. We conclude that better-looking images are neither necessary nor sufficient; restoration modules must be task-driven, selective, and physically aware. Code, pretrained models, and recipes are provided for integration.
Read the full abstract ▾
All authors Lanqing Guo, Xijun Wang, Minchul Kim, Yu Yuan, Wes Robbins, Xingguang Zhang, Nicholas Chimitt, Stanley H. Chan, Zhangyang Wang, Xiaoming Liu
Machine Learning
PPDL: A Real-world Industrial User Retention Ratio Forecasting Framework Integrating Physical Priors with Deep Learning
Zibo Zhao, Zhengxiong Guan, Chaoli Zhang et al. (+4 more)
In multi-channel paid user acquisition, early and accurate prediction of user retention at the channel level is crucial for optimizing budget allocation. User retention curves display a pronounced temporal pattern: an initial period of high churn transitions into long-term stability. This pattern is further characterized by regular fluctuations attributable to seasonality and exhibits high serial autocorrelation. These intrinsic properties make such curves highly suitable for analysis within a time-series
forecasting framework. However,
forecasting user retention ratio for large-scale short-
video platform faces three major challenges: significant heterogeneity across channels, pronounced global trend of decay followed by saturation, and short look-back windows. To address these challenges, we propose PPDL, a novel
forecasting framework that integrates physical priors with deep learning. We first introduce a trend-residual decomposition component. The trend is modeled using the Weibull distribution, whose parameters are learned via a Multilayer Perceptron (MLP). Secondly, for the residual component, we design an auxiliary
embedding module on top of a deep learning backbone to maintain the channel identity awareness. Finally, to enhance the model's sensitivity to trends, we design a Multiscale Trend-penalized loss function. The proposed approach PPDL is validated through comprehensive experiments on industrial-scale
datasets, covering three applications with an average of 30+ channels each. Experimental results show that PPDL achieves improvements across different backbones and significantly outperforms existing online solutions.
Read the full abstract ▾
All authors Zibo Zhao, Zhengxiong Guan, Chaoli Zhang, Linyuan Geng, Xuanbing Zhu, Zhonglong Zheng, Fan Wu
Human-Computer Interaction
What Makes a Great Co-Worker in an AI-Native Workplace?
Rudrajit Choudhuri, Max Meijer, Sam Yu-Te Lee et al. (+6 more)
As knowledge work grows interdependent between humans and AI, we ask what makes a great co-worker in an AI-native workplace. To answer this, we conducted 22 interviews and a large-scale mixed-methods survey of 1,534 knowledge workers at a multinational technology company. We contribute BACI, a framework of 75 co-worker qualities that apply to humans and AI, spanning Benevolence, Ability, Cooperativeness, and Integrity. Comparing priorities for humans and AI identified 11 co-worker archetypes and revealed disagreement over whether AI should have warmth, take initiative, or own outcomes. We also show how priorities for these archetypes varied with workers' individual characteristics. Lastly, we contribute a taxonomy of AI work etiquette capturing the obligations co-workers expect of one another when preparing, sharing, and taking responsibility for AI-supported work. Based on these findings, we derive implications to inform worker-centric AI and workplace design.
Read the full abstract ▾
All authors Rudrajit Choudhuri, Max Meijer, Sam Yu-Te Lee, Cinoo Lee, Caolan Mannion, Peter Jahn, Anita Sarma, Christian Bird, Alice Ferng
Artificial Intelligence
Partition Scores Are Not System Scores: Deployment-Fidelity Gaps in Decomposed Algorithm Selection
Jiachen Zhang, Yu Tang and Li Zhu
Oracle-style quantities, including virtual best solvers, selected-portfolio VBS, virtual-best encodings, and best-in-family summaries, are widely reported as upper bounds on what a deployable selector could achieve. In decomposed
algorithm selection, an analogous partition-level score grants an oracle choice of the best
algorithm within the selected family; once the family selector is fixed, the deployable system must replace that within-family oracle with a learned within-family selector. We define the deployment-fidelity gap G(R) as the difference between partition-level and deployable end-to-end utility and derive two accounting consequences: a per-instance margin-regret stability condition that tells us when a partition-time family choice is deployment-optimal, and a sharp partition-only identification interval that, when it strictly crosses zero, prevents the partition-level report from certifying the deployable winner. Across five public
algorithm-selection
benchmarks spanning tabular AutoML and combinatorial CSP/SAT, every decomposed pipeline has positive G(R), ranging from 0.012 on TabZilla to 0.13 on PROTEUS-2014. Four of ten decomposed-versus-flat decisions have sign-changing point estimates; on PROTEUS-2014, a 33-point partition advantage shrinks to a 20-point end-to-end advantage. A training-side validation gap-correction diagnostic recovers the point-estimate deployable sign on all four sign-changing
cells; it is a reporting aid, not a substitute for direct end-to-end evaluation. Partition and end-to-end scores should be reported side by side.
Read the full abstract ▾
Numerical Analysis · Cross-listed from math.AP
Ground states to bi-harmonic nonlinear Schrödinger equations with competing dispersion
Christian Klein and Svetlana Roudenko
We study ground-state solutions of the 4th order nonlinear Schrödinger equation with mixed dispersion via the
elliptic profile equation $\Delta^2 Q + 2a \Delta Q + bQ - |Q|^\alpha Q=0$, focusing on
symmetry breaking of least-action ground states in 2D in the regime $a=1$, $b=1+\epsilon$, $0<\epsilon \ll 1$, where nonradiality was proved by Lenzmann and Weth [26]. We establish a quotient-to-mass relation converting small-$\epsilon$ asymptotics of the Weinstein quotient into mass asymptotics, in any dimension and
symmetry class. In 1D we prove the sharp small-$\epsilon$ rate for the quotient for every $\alpha>0$ and deduce the rates for the mass, action and potential norm. In two and higher dimensions the same relation, combined with the quotient asymptotics of Lenzmann-Weth [26] and Mandel-Oliveira e Silva [27], gives the mass rates for the Knapp-type nonradial and the radial ground states. The resulting threshold $\alpha_K(d)=8/(d+1)$ coincides for $d\leq3$ with the existence of normalized minimizers threshold of Fernández-Jeanjean-Mandel-Mariş [16], connecting the least-action and mass-constrained formulations. We complement this with a detailed numerical study. For the cubic nonlinearity we construct a nonradial branch from a Knapp-type example, compare it with radial and angular-mode branches, and verify the predicted rates. For the quartic nonlinearity, turning points and branching are present in the mass-energy diagrams in radial or two- and four-peak nonradial solutions. Here, although least-action ground states are nonradial for small $\epsilon$, the normalized ground states of the same mass appear radial, a consequence of branching. For $\alpha\geq4$ we find only radial ground states, consistent with the conjectured sharp form of the Stein-Tomas inequality on $\mathbb S^1$, equivalent to the radial and nonradial masses having the same leading coefficient.
Read the full abstract ▾
Cryptography and Security
PQLN: Post-Quantum Security for the Bitcoin Lightning Network's Off-Chain Surfaces
Ahmet Kurt, Abdul-Salem Beibitkhan, Yacoub Hanna et al. (+1 more)
A cryptographically relevant
quantum computer will break the
elliptic-curve cryptography behind Bitcoin and its Lightning Network, the most widely used payment channel network. Even a post-
quantum consensus upgrade of Bitcoin would not cover Lightning's off-chain surfaces, so its gossip, peer transport, invoices, payment onions, and offers need separate protection. An adversary can already record Lightning's encrypted traffic today and decrypt it once such a computer exists. Lightning can therefore move to post-
quantum cryptography now, without waiting for Bitcoin, and stop such harvest-now-decrypt-later attacks along with node impersonation, invoice forgery, and payment deanonymization. In this paper, we propose PQLN, a hybrid post-
quantum extension of Lightning that protects all of these surfaces with the
lattice-based standards ML-DSA and ML-KEM. PQLN distributes post-
quantum node identities through Lightning's gossip, hybridizes the transport handshake, adds post-
quantum signatures to invoices, commits post-
quantum keys in offers, and makes payment onions hybrid. Since post-
quantum material is much larger than its
elliptic-curve counterpart, we introduce techniques that fit it into Lightning's existing message formats and size limits. We analyze the security of PQLN against a
quantum adversary and implement it in rust-lightning, a major Lightning implementation. Our evaluation with real Lightning nodes shows that PQLN nodes interoperate with unmodified nodes. The added cryptographic operations take at most 0.33 milliseconds, and the main cost is communication, since gossip data grows about tenfold with ML-DSA and about fourfold with the smaller Falcon. To our knowledge, PQLN is the first post-
quantum design, implementation, and evaluation for Lightning.
Read the full abstract ▾
All authors Ahmet Kurt, Abdul-Salem Beibitkhan, Yacoub Hanna, Abdullah Aydeger
Logic in Computer Science
Mechanizing Gödel's Incompleteness Theorems and Provability Logic
Shogo Saitou and Mashu Noguchi
We mechanized proof of Gödel's first and second incompleteness
theorems, Solovay's arithmetical completeness
theorem of \mathbf{GL}, and related results in the Lean 4
theorem prover.
Robotics
Force-Aware Reinforcement Learning with Hybrid Sensorless Force Estimation for Wheeled-Legged Loco-Manipulation
Xuanqi Zeng, Jiaming Wang, Tianlin Zhang et al. (+5 more)
Force-controlled loco-manipulation requires a whole-body policy to coordinate locomotion and arm motion while regulating end-effector interaction forces. This is challenging under floating-base dynamics and changing support contacts, particularly when end-effector force/torque sensing is unavailable for control. This paper presents a force-aware reinforcement learning approach with hybrid sensorless force estimation for wheeled-legged loco-manipulation. The proposed method provides a structured estimate of the end-effector force as an explicit policy observation, enabling force-guided contact behavior without using an end-effector force/torque sensor for control. The force estimate is obtained by combining generalized momentum observation, contact-constrained wrench projection, and temporal residual learning: the model-based components extract the physically structured part of the whole-body disturbance, while the residual network compensates the remaining motion-dependent bias. The estimated force is integrated into a mode-conditioned whole-body policy with an axis-wise force/position selector, allowing free-space motion, pure force regulation, and hybrid force/position control within one controller. Simulation results demonstrate improved sensorless force estimation and force-control performance. Hardware experiments further validate the proposed controller through quantitative valve-rotation and hybrid wiping evaluations, together with force-guided door opening and zero-force human-guided motion on a real wheeled-legged platform.
Read the full abstract ▾
All authors Xuanqi Zeng, Jiaming Wang, Tianlin Zhang, Lingwei Zhang, Botian Xu, Weipeng Xia, Zhongyu Li, Yun-Hui Liu
Computer Vision
GEAR: From Dynamic Encoding to Dynamic Activation in Social Trajectory Prediction
Jiaheng Chen, Jiaxing Li, Leixia Wang et al. (+2 more)
Human trajectory prediction requires modeling both individual motion patterns and social interactions among
agents. Existing methods have made substantial progress by using
attention mechanisms, graph structures, and temporal encoders to capture dynamic social context. However, most of them primarily focus on how social information is encoded, while paying less explicit
attention to how the encoded social context should take effect during future trajectory generation. In this paper, we argue that dynamic social encoding does not necessarily imply dynamic social activation. The same interaction context may require different activation strengths across future horizons and scene densities: social cues should be strengthened when interaction evidence is strong, but suppressed when they are weak or noisy. To address this issue, we propose GEAR, a generation-aware bias activation model for human trajectory prediction. Built upon a bias-decomposed trajectory generation formulation, GEAR dynamically activates the individual-motion and social-resonance bias terms at each future step before final trajectory composition. This allows the model to explicitly control when and how strongly individual and social bias components participate in generation. Experiments on ETH-UCY, SDD, and NBA show that GEAR consistently improves the resonance-based baseline and achieves competitive state-of-the-art performance. Further analyses of activation patterns and density-grouped errors validate the importance of calibrating encoded social context during trajectory generation. Our code is available at https://github.com/11isnotavailable/GEAR.git.
Read the full abstract ▾
All authors Jiaheng Chen, Jiaxing Li, Leixia Wang, Jianan Ju, Tinghe Zhang
Robotics
When Do Learned Priors Help Visual Inertial Estimation? A Controlled Study of Prior Integration, Calibration, Initialization, and Backend Consistency
Jinchang Zhang and Guoyu Lu
Learned components are increasingly integrated into
geometric visual–inertial
estimators to provide motion, depth, bias, uncertainty, or confidence cues. Yet it remains unclear whether gains arise from useful learned priors or from changes in the backend, calibration, initialization, temporal association, or evaluation gauge. We present a controlled framework for learning-augmented visual–inertial estimation that separates fusion gain from the incremental value of a learned prior and evaluates four evidence layers: local motion consistency, global trajectory accuracy, physical-state correctness, and numerical consistency. We instantiate the framework with a MonoViT-based
monocular motion prior added as a local relative-motion factor to an unchanged VINS backend. We compare Original VINS and learned-prior VINS under matched sensor streams, timestamps, initialization, frontend/backend settings, and camera–IMU extrinsics, while probing calibration, initialization, state coupling, scale, bundle adjustment, and loop closure. On KITTI, with fixed reference extrinsics, translation APE RMSE is 31.4 m for Original VINS and 31.8 m with the learned prior. Across four recordings, the prior changes mean APE by only -0.2%, while a five-times-higher weight worsens it by 8.2%. Online extrinsic updates increase mean APE by 45.7% and 52.1%, respectively, while mean RPE changes by less than 2%. These results show that fusion performance alone cannot establish the value of learned priors. Reliable evaluation requires same-backend controls and joint analysis of prior compatibility, calibration, initialization, global drift, physical-state error, and backend consistency.
Read the full abstract ▾
Artificial Intelligence
Surprising Effectiveness of Self-Demonstrations in Enhancing Schema-Ontology Mapping with LLMs
Siddhesh Thombre, Manasi Patwardhan and Sunita Sarawagi
Integrating heterogeneous relational databases into a centralized ontology remains a persistent challenge in enterprise knowledge representation, primarily due to semantic heterogeneity, cryptic schema naming, missing metadata, and the abstraction gap between relational schemas and ontological models. Although large
language models (LLMs) offer strong semantic
reasoning capabilities, we show that directly applying them through one-shot prompting or naive multi-stage pipelines leads to poor performance for schema-ontology mapping. This paper presents a self-demonstration-driven approach that combines a neuro-symbolic task decomposition with a novel mechanism for automatically generating pattern-guided, dependency-aware demonstrations to address this integration challenge. Our approach incorporates two key strategies to achieve substantial accuracy gains over existing LLM-based schema integration methods: (i) a neuro-symbolic decomposition of the task into cascaded sub-tasks, where symbolic constraints structure the search space and LLMs perform semantic
reasoning within each focused sub-task, and (ii) self-generated demonstrations guided by domain-agnostic patterns to supervise each sub-task. Experiments on three of the most challenging scenarios from the RODI
benchmark show that our approach achieves state-of-the-art performance, substantially outperforming (25 percentage points F1 improvements) both traditional schema-to-ontology mapping techniques and recent LLM-based schema-to-ontology and schema matching approaches. Ablation studies further reveal the significant benefits of pattern-guided self-demonstrations and the complementary benefits of neuro-symbolic task decomposition.
Read the full abstract ▾
Systems and Control
From Benchmark to Deployment: Shift-Robust Fabric Recognition for Industrial Textile Onboarding
Haochen Li, Chenwei Wang, Felicity S.C. Tang et al. (+3 more)
Automatically recognising a fabric's construction (jersey, twill, satin) is a bottleneck in textile sourcing, where incoming swatches are still typed by hand.
Benchmark accuracy suggests the problem is solved, yet rarely survives deployment. On the \numClasses{}-class FabricFlow
benchmark we expose three gaps that headline accuracy hides. First, a duplication audit reveals train/test leakage that inflates accuracy; we rebuild leakage-free splits that report the true difficulty. Second, on the clean data the binding failure is acquisition-source shift between catalogues, not the peripheral shortcuts one might fear: on an archive-exclusive hold-out, standard training holds 58.0% Top-1 at a calibration error of 0.158, while a simple, architecture-agnostic central-texture recipe adds 13.5 Top-1 points and restores calibration. Third, because confusing one fabric family for another is costlier than a within-family slip, we optimise a taxonomic-severity cost: a confidence-gated routing policy auto-types confident swatches and refers only the uncertain minority to a human, sharply cutting onboarding cost. Throughout we report honest negatives: hierarchical classification, OCR fusion and zero-shot
vision–
language models all fail to help, yielding a concrete, calibrated, cost-aware recipe for deployable textile onboarding.
Read the full abstract ▾
All authors Haochen Li, Chenwei Wang, Felicity S.C. Tang, Misbah Iqbal, Carman K. M. Lee, Elif Ozden Yenigun
Machine Learning
Does Reasoning Improve Psychological Depth in Large Language Models? It Depends on Who's Judging
Ruichen Zheng, Yihe Wang, Fabrice Y Harel-Canada et al. (+4 more)
LLM-as-a-Judge evaluators are increasingly used to score open-ended generation, yet a judge's correlation with human ratings on its development set may not guarantee valid measurement when outputs are closely matched and human preferences are subjective. We study this failure mode through psychological depth in short stories. Seven human readers and an LLM-judge ensemble selected on the original scalar Psychological Depth Scale
dataset ($\rho = 0.646$) evaluated 60 blinded,
prompt-matched story pairs from GPT-5 vs.\ GPT-4o and DeepSeek-R1 vs.\ DeepSeek-V3. Human preferences showed no universal
reasoning advantage: GPT-5 was modestly preferred over GPT-4o (60.0–62.9%), whereas DeepSeek-R1 trailed V3 (42.9%), and inter-reader agreement was near chance (Krippendorff's $\alpha = 0.070$), with within-reader consistency and recurring weighting patterns suggesting structured heterogeneity rather than random responding. The judge, by contrast, favored
reasoning outputs in 89.0% of dimension-level comparisons and 59 of 60 pairs on aggregate PDS, uniformly across all five evaluator configurations, and its scores were associated with surface features such as sentence length and lexical diversity. These results suggest that development-set performance is insufficient evidence for deployment validity on a shifted distribution, and that point-estimate judges can obscure the heterogeneity in subjective human evaluation.
Read the full abstract ▾
All authors Ruichen Zheng, Yihe Wang, Fabrice Y Harel-Canada, Sara Khosravi, Zeynep Senahan Yildiz, Amit Sahai, Nanyun Peng
Artificial Intelligence
Homeostatic Continual Learning
Yue Jin
In this paper, I formulate a Continual Learning problem and propose a method named "Homeostatic Continual Learning" that enables an AI
agent to learn continuously in a changing environment without catastrophic forgetting. The core of the method is to find outliers in the environment data when the
agent experiences an outlier in its output. Through this method, the
agent gradually completes its model and policy and performs well in more and more contexts. I also suggest that we may use the method to build a world model where the
agent factorizes the objects in the world into features, abstract objects into comparable instances of concepts and map concepts to intents through features. I discuss the works needed to render the method practical, the connections to many fields in Artificial Intelligence and the broader implications of the method.
Read the full abstract ▾
Machine Learning
Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation
Yilei Tu, Zihao Li, Shaoxiong Ji et al. (+2 more)
Specialist
distillation effectively transfers domain expertise to student models via teacher-generated
reasoning trajectories. However, when these specialists are trained solely on question–answer pairs without explicit
reasoning supervision, what governs the trajectories they generate? In this work, we show that specialist optimization implicitly selects from this latent trajectory space. To isolate and observe this latent distribution, we leverage student
distillation not as a downstream goal, but as an agnostic probe—since students inherit no parameterization or optimization constraints from the specialist, inheriting only the sampled trajectories themselves. Through this probe, our empirical analysis unveils a tight governing relationship: across 27 specialist–student pairings, their specialization–generalization profiles correlate exceptionally strongly. Crucially, explicitly controlling the specialist's distributional drift systematically shifts both the teacher and its distilled student along a controllable trade-off between domain precision and general-capability retention. Across chemistry, physics, and
multilingual settings, distilled students systematically reflect these specialist-induced profiles, even across divergent model families. Our findings establish a new view of specialist training: when gold
reasoning is absent, tuning choices directly control the latent supervision passed to downstream models.
Read the full abstract ▾
All authors Yilei Tu, Zihao Li, Shaoxiong Ji, Jörg Tiedemann, Fei Yuan
Computation and Language
HyperProve: Answer-Guided Hypergraph Expansion for Multi-Hop Question Answering
An Nguyen Phu, Dung Nguyen Quang, Luu Hieu An et al. (+3 more)
Multi-hop question answering often fails when
retrieval treats evidence as isolated matches to the original question, since the facts needed to answer a complex question are usually connected through intermediate entities, relations, and constraints. We propose HyperProve, a
retrieval-augmented QA framework that addresses this challenge by coupling question decomposition with answer-conditioned expansion over a hypergraph of atomic facts. HyperProve does not use atomic facts, hypergraphs, or iterative
retrieval in isolation; instead, it carries intermediate answers and supporting hyperedges as
retrieval state, then uses that state to bias the next local hypergraph expansion. This design enables HyperProve to construct coherent evidence chains for final answer generation while making the
retrieval process stateful and fact-centered. Across multi-hop QA
benchmarks, HyperProve achieves the best overall performance in our evaluation, outperforming the strongest baselines by an average relative improvement of 6.2% in answer accuracy and 4.9% in F1.
Read the full abstract ▾
All authors An Nguyen Phu, Dung Nguyen Quang, Luu Hieu An, Linh Ngo Van, Trung Le, Thien Huu Nguyen
Robotics
Learning In-Hand Object Reaching to General 6D Poses
Junxiao Lin, Tianyue Wu, Jie Yin et al. (+3 more)
In-hand manipulation allows multi-fingered dexterous hands to reconfigure grasped objects without releasing and regrasping them. This improves manipulation efficiency by reducing repeated grasp acquisition and large arm motions. However, most learning-based methods focus on reorientation, continuous rotation, or translation, whereas many tasks require joint control of object position and orientation. We formulate this capability as in-hand 6D object pose reaching: starting from an existing grasp, coordinated finger motions move the object to a palm-relative target pose. We present POISE (Palm-relative Object reaching In SE(3)), a sim-to-real reinforcement learning framework for this task. POISE combines diverse stable-grasp initialization, goal- and geometry-conditioned control, an adaptive 6D goal curriculum, and a compact reward scheme for pose reaching and grasp preservation. In simulation, diverse initialization raises held-out-grasp success from 40.1% to 51.5% and post-drop recovery from 33.8% to 72.9%; the curriculum raises full-range success from 6.2% to 59.5%. On hardware, the grasp-maintenance reward improves three-target sequence success from 20% to 80%. In real-world experiments, POISE reaches successive 6D targets without manual reset across multiple object geometries and wrist orientations, and recovers from external disturbances. To support further research in dexterous manipulation, we will release our code at https://junxiaolin.github.io/poise-website/.
Read the full abstract ▾
All authors Junxiao Lin, Tianyue Wu, Jie Yin, Jia Pan, Kaifeng Zhang, Weiming Zhi
Artificial Intelligence
Positioning manuscripts in the scientific landscape with agentic AI
Jiawen Chen, Zichen Zhang, Bingxuan Li et al. (+7 more)
Publishing a research manuscript is a routine yet demanding part of scientific life: time-consuming, stressful, and often uncertain in outcome. Recent advances in large
language model (LLM)-based agentic AI have shown promise across a range of scientific tasks, and here we ask whether agentic AI can help researchers navigate the publication process itself by reliably inferring a manuscript's eventual publication venue from its content and literature context. We introduce PASS (Publication-oriented Agentic Scientific System), an agentic system that understands manuscripts within their domain-specific literature context and predicts top-matched publication venues. PASS positions each manuscript within its surrounding literature landscape by reconstructing its local scientific neighborhood, tracing its topic trajectory, and
reasoning over field-specific journal spaces. Evaluated on a leakage-audited
benchmark of over 2,000 preprints across 16 biomedical fields, PASS achieved Top-1 accuracy of 50.3% and Top-5 accuracy of 86.1%, outperforming state-of-the-art LLM baselines and established journal-selection tools. PASS-produced quality scores, such as impact potential and novelty, aligned with independent measures of publication outcome. We also found that the designed literature
retrieval module is the strongest performance contributor, particularly for positioning manuscripts relative to nearby work, and that PASS maintained near-full performance from the abstract alone, whereas LLM baselines required the full manuscript text. An independent human evaluation found strong researcher agreement with PASS's manuscript understanding and recommendation rationale. PASS has been released as a public platform (https://ratemypaper.ai/) for broad researcher access.
Read the full abstract ▾
All authors Jiawen Chen, Zichen Zhang, Bingxuan Li, Quan Sun, Yiyan Zhang, Edric Tam, Jinjie Lin, Didong Li, Yun Li, Bingxin Zhao
Artificial Intelligence · Cross-listed from math.OC
On the Equivalence of Stochastic Control and Path Space Formulations for Schrödinger Bridges over Compact Connected Lie Groups
Hamza Mahmood, Georgiy A. Bondar, Abhishek Halder et al. (+1 more)
We establish the equivalence between the
stochastic optimal control and path space formulations of the Schrödinger bridge problem (SBP) for the kinematic equation on a compact connected Lie group. Using the
geometric concepts of horizontal lift and
stochastic anti-development, we derive a Girsanov-type change-of-measure result, and show that the expected control energy equals the relative
entropy of the controlled path law with respect to the reference Wiener measure. Thus, the SBP is equivalently a path space relative
entropy minimization problem subject to prescribed endpoint marginals.Our result has three useful implications. From an analytic viewpoint, the shown equivalence helps prove the existence and uniqueness of the SB. From a probabilistic viewpoint, it helps interpret the SB as the most probable deviation of the uncontrolled
stochastic dynamics consistent with the endpoint constraints. From a computational viewpoint, it allows using static Sinkhorn recursions to directly solve the relative
entropy minimization problem and compute the optimal path measure. We illustrate the equivalence numerically on the
torus $\mathbb{T}^2$. The code is publicly available at: https://github.com/gradslab/LargeDeviationSBP
Read the full abstract ▾
All authors Hamza Mahmood, Georgiy A. Bondar, Abhishek Halder, Adeel Akhtar
Computer Vision
Development of Low-Cost Real-Time Driver Drowsiness Detection System using Eye Centre Tracking and Dynamic Thresholding
Fuzail Khan, Sandeep Sharma and M. R. Arulalan
One in every five vehicle accidents on the road today is caused simply due to driver fatigue. Fatigue or otherwise drowsiness, significantly reduces the concentration and vigilance of the driver thereby increasing the risk of inherent human error leading to injuries and fatalities. Hence, our primary motive being - to reduce road accidents using a non-intrusive image processing based alert system. In this regard, we have built a system that detects driver drowsiness by real time tracking and monitoring the pattern of the driver's eyes. The stand alone system consists of 3 interconnected components - a processor, a camera and an alarm. After initial facial detection, the eyes are located, extracted and continuously monitored to check whether they are open or closed on the basis of a pixel-by-pixel method. When the eyes are seen to be closed for a certain amount of time, drowsiness is said to be detected and an alarm is issued accordingly to alert the driver and hence, prevent a casualty.
Read the full abstract ▾
Mathematical Software · Cross-listed from math.OC
Row-Polar LP-Newton for Linear Programming with Corral Repair
Yanfei Li, Yuki Matsuno and Jianming Shi
LP-Newton solves a linear program through a sequence of nearest-point problems. Given an interior feasible point for an inequality-form LP, we construct the compact hull formed by the origin and its normalized constraint rows. Polar LP-Newton (P-LPN) follows the objective ray to the boundary of this row-polar hull, where it recovers a primal-dual optimum or a recession direction proving unboundedness. For rational row-polar data, we prove an outer-iteration bound quadratic in dimension and linear in binary input length, excluding inner Wolfe work. Restarting Wolfe at every outer iteration discards its terminal corral even though the hull is unchanged and the next target lies on the same ray. Corral-repair P-LPN (CR-P-LPN) instead repairs that corral and uses it to start the next projection. Verification over the full hull preserves P-LPN's projections, outer targets, and LP conclusion in exact arithmetic. Experiments in Julia and MATLAB show where repair helps. After common initialization, median P-LPN times across 180 single-LP tests are 1.62 times the corresponding CR-P-LPN times in Julia and 1.55 times in MATLAB. On three problems with 5,000 to 100,000 rows, the corresponding
geometric-mean factors are 2.03 and 1.46. A separate end-to-end study includes initialization on 19 application-derived LPs. CR-P-LPN has lower median total time than the faster cold HiGHS mode, either dual simplex or the interior-point method with crossover, on 18 of the 19 workloads in each
language. The
geometric means of the ratios of HiGHS time to CR-P-LPN time are 4.93 and 3.06. Component comparisons identify terminal-corral reuse as the useful component, whereas candidate-first ordering alone shows no consistent gain. Repair is not always beneficial: it is slower on Klee-Minty tests, and an author-implemented simplex is faster on the retained Netlib models.
Read the full abstract ▾
Artificial Intelligence
How Should Reasoning Be Organized in a Transformer's Latent Space?
Hongyu Gu, Chang Liu and Jingwen Fu
Continuous
reasoning has emerged as a promising way to improve
reasoning in large
language models (LLMs). Yet we still lack a clear principle for deciding what a latent state should preserve.
Reasoning by superposition shows that a single latent state can encode several search alternatives and expand them in parallel. We ask how those states should be weighted as
reasoning proceeds. A natural choice is to preserve only the states active at the frontier step, since keeping every reached state appears to spread a limited hidden width too thin. We show that the opposite can hold. When later computation draws on several reached states, a cumulative state can guide
attention correctly at a smaller hidden width than a frontier state that stores fewer states. At the same width, the cumulative state therefore keeps more intermediate states available for later
reasoning. More generally, equal cumulative weights are optimal when future queries are unknown and remain close to the best task-specific weights when those queries are known. Experiments with two-layer and GPT-2
Transformers reproduce the predicted width advantage and show that unequal weights fail first on the states that receive the least weight. This suggests a important principle: keep reached states equally weighted, and restore equal weights as computation proceeds.
Read the full abstract ▾
Systems and Control
Low-Ripple Modulation Strategy for a Photovoltaic-Based Triple-Port Hydrogen Production System
Shiqi Zhang, Ziang Jiao, Jiaxin Su et al. (+4 more)
Among various production methods, hydrogen generation via electrolysis powered by renewable energy plays a key role in achieving large-scale green hydrogen production. The triple active bridge isolated DC-DC conversion system exhibits significant application potential in hydrogen production due to its advantages, such as high energy density, wide step-down ratio, and high reliability. However, the output current ripple at the hydrogen production port critically affects the efficiency of the electrolyzer and the hydrogen production rate. Existing studies have limited optimization effects on current ripple and struggle to achieve dynamic optimization, leading to constrained ripple suppression under dynamic operating conditions. To address this issue, this paper proposes a low-ripple modulation strategy based on coordinated optimization of inner and outer phase-shift angles for multi-port power conversion systems in renewable energy hydrogen production. By establishing an accurate mathematical model, the optimal phase-shift angle combination under minimal current ripple conditions is derived. An improved differential
evolution algorithm with adaptive parameter strategy is employed to achieve global optimization under dynamic conditions. Simulation and experimental results demonstrate that the proposed strategy effectively suppresses current ripple, providing an efficient and reliable solution for hydrogen production from fluctuating renewable energy sources.
Read the full abstract ▾
All authors Shiqi Zhang, Ziang Jiao, Jiaxin Su, Ning Wang, Zheng Li, Xiaoqiang Guo, Changchun Hua
Computation and Language
Inside VLM Chart Reading: Tracing Value Reading from Vertical Bar Charts Across Space and Depth
Tianhao Niu, Qingfu Zhu and Wanxiang Che
Vision-
language models (VLMs) can answer chart questions accurately, but output accuracy alone provides limited insight into the internal representations supporting exact value reading. We study value reading from vertical bar charts through controlled counterfactual activation patching in Qwen2.5-VL-7B-Instruct and InternVL3.5-8B. Our study connects three analyses. First, under one-tick bar-height counterfactuals, patching states selected by the changed-height region produces greater restoration of the original answer preference than patching states selected by the invariant bar body. Across
language-model depth, restoration from legend- and series-related positions declines earlier than restoration from bar-geometry and axis-scale positions. Second, we identify middle-layer states at series-related
prompt positions that can restore answer preference under legend swaps. Resetting these states selectively weakens restoration from an earlier visual-legend patch, demonstrating their causal role in the downstream effects of that intervention. Third, a factorial analysis shows that both models can combine geometry and scale states from separate donors to favor the combined target answer. Together, these results provide causal evidence about the internal states supporting exact bar-value reading.
Read the full abstract ▾
Computer Vision
Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction Tuning
Kunlun Xu, Yanqin Zhang, Wenwen Qiang et al. (+1 more)
Multimodal Continual Instruction Tuning (MCIT) aims to exploit the incrementally accumulated knowledge to process
multimodal inputs of diverse tasks, where parameter routing plays an important role. State-of-the-art methods rely on sample-to-task center similarity and cross-modal fusion with equal weight during routing. However, such solutions face two fundamental flaws: (1) Within each modality, the sample-to-task center distance is sub-optimal for routing since the abundant intra-task diversity information is underleveraged. (2) Different modalities exhibit varying reliability across tasks, where the modality with inter-task ambiguity can easily misguide the routing result. To address these problems, we propose
Hyperbolic Uncertainty-aware Modality-Balanced Routing (Hyper-LLaVA) to improve parameter routing capacity based on cross-modality task feature uncertainty modeling. Specifically, to improve intra-modality task matching, Hyper-LLaVA accesses the sample-to-task distribution similarity in the
Hyperbolic space. Besides, to alleviate the degradation brought by unreliable modalities, Hyper-LLaVA quantifies the task matching ambiguity within each modality to achieve adaptive balancing between task matching across modalities. Based on the complementary intra- and inter-modality task matching enhancement, our Hyper-LLaVA outperforms state-of-the-art approaches by large margins. Our source code is available at https://github.com/zhoujiahuan1991/ICML2026-Hyper-LLaVA
Read the full abstract ▾
All authors Kunlun Xu, Yanqin Zhang, Wenwen Qiang, Jiahuan Zhou
Machine Learning
HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement Learning
Hongliang Wei, Xiaobing Tu, Yinggui Wang et al. (+6 more)
Language-model
agents are increasingly deployed through diverse harnesses that differ in system
prompts, tool schemas, control loops, and trajectory formats. The same model can perform unevenly across these interfaces, making robustness to harness variation an important objective. A natural approach is to train a shared policy through multiple harnesses, but doing so introduces a scheduling problem: each training step should favor a harness that currently provides a useful learning signal while also producing an update that benefits the other harnesses. We develop HarnessBandit, an online scheduler that selects one harness per optimizer step. After a group-relative policy optimization (GRPO) update, it observes learnability – the mean absolute advantage on the batch – and transferability – the cosine between a low-dimensional gradient sketch of the current harness and exponential moving averages of the remaining harnesses. The two signals are fused after pooled sliding-window min-max normalization and sampled with a visit-dependent bonus and an explicit exploration floor. We train Qwen3.5-2B across six harnesses on ClawGym and evaluate on PinchBench (held-out tasks, in-distribution OpenClaw) and ClawEval (held-out tasks and harness). HarnessBandit improves over mixed-batch multi-harness training on both
benchmarks, while training diagnostics indicate that learnability and transferability provide distinct, evolving signals.
Read the full abstract ▾
All authors Hongliang Wei, Xiaobing Tu, Yinggui Wang, Zhengxi Liu, Rongkun Xue, Jinkui Ren, Xiantao Zhang, Debin Zhao, Xiaopeng Fan
Computation and Language
ForeSight: Enhancing Risk Monitoring via Early Safety Signal Distillation
Hanling Wang, Chenlong Wei, Ling Xu et al. (+6 more)
As large
language models (LLMs) are increasingly deployed, the generation of harmful content has become a critical safety concern. Existing safeguards operate at the input, output, or streaming-generation stages, while early-risk methods that rely on surface
tokens or output logits may suffer from weak initial signals, and internals-based detectors using dense representations may retain highly entangled and redundant safety-irrelevant information. It therefore remains unclear whether the earliest post-generation hidden states already contain reliable signals about final-response harmfulness. To address this gap, we propose ForeSight, a first-
token output-risk
forecasting framework that distills weak and redundant early safety signals into compact, layer-aware risk representations. Experiments on five safety
benchmarks and two target models demonstrate that ForeSight achieves superior and efficient early-risk
forecasting while relying solely on first-
token hidden states. The code is available at: https://github.com/Scabbards1500/Foresight
Read the full abstract ▾
All authors Hanling Wang, Chenlong Wei, Ling Xu, Hanyan Niu, Qi Cao, Shizhou Huang, Yang Yang, Xiaohui Zhu, Yao Zhu
Computation and Language
PolicyMem: Geometric Policy Memory for LLM Governance
Yuanchen Bei, Zhengzhang Chen, Yanjun Zhao et al. (+3 more)
Effective LLM governance extends beyond detecting unsafe responses to guiding their correction through closed-loop assessment, revision, and verification. Learning-based guards provide strong semantic discrimination but often leave policy knowledge implicit in trained parameters, limiting its explicit reuse across stages. Programmable guardrails make policies explicit through
prompts and workflows, but rely heavily on manual engineering to operationalize them. This motivates explicit policy representations that are both learnable and reusable across governance operations. To this end, we introduce PolicyMem, a
geometric policy
memory that compiles natural-
language policies into learnable low-rank subspaces for reuse across governance stages. A policy assessor projects query-response representations onto these subspaces, producing evidence that directly mediates safety judgments and policy attribution. A response rewriter uses the implicated policies to revise unsafe responses, with the same assessor re-evaluating the revised responses. Beyond inference, the same
memory constructs training data from model-generated candidates to supervise the rewriter without external teacher calls. Across five widely used
benchmarks, PolicyMem achieves the best average unsafe-behavior detection performance among representative baselines while supporting effective policy attribution, rewriting, and post-intervention assessment through the shared policy
memory.
Read the full abstract ▾
All authors Yuanchen Bei, Zhengzhang Chen, Yanjun Zhao, Haoyu Wang, Hanghang Tong, Haifeng Chen
Computer Vision
FFVO: A Feedforward Pose Decoder for Long-Horizon Visual Odometry
Meng-Li Shih, Shih-Yang Su, Yuliang Zou et al. (+7 more)
Stable and reliable 4D spatial understanding is fundamental for autonomous driving systems. While feedforward reconstruction networks can estimate camera motion and 3D structure in one pass, pose estimation over long
videos remains challenged by computational cost, long-context ambiguity, and temporal instability. To address these challenges, we propose Feedforward Visual Odometry (FFVO), a pose-specialized adaptation of joint reconstruction architectures for efficient and temporally stable camera-pose estimation. FFVO uses (i) a compact camera-
token representation for computationally efficient temporal aggregation, (ii) a hierarchical local-to-global temporal decoder that mitigates
geometric ambiguity by separating short-range motion aggregation from sequence-level integration, and (iii) intermediate trajectory supervision that promotes temporal stability. Extensive evaluation on the Waymo Open
Dataset (WOD), KITTI, and a large-scale proprietary
benchmark demonstrates that our method performs favorably against existing feedforward approaches, and greatly reduces jitter and drift. These results support FFVO as an effective feedforward camera-pose decoder in long-horizon visual odometry settings.
Read the full abstract ▾
All authors Meng-Li Shih, Shih-Yang Su, Yuliang Zou, Hao Xiang, Haidong Zhu, Vincent Casser, Brian Curless, Dmitry Kalenichenko, Mingxing Tan, Dragomir Anguelov