Peer Revenue Fully funded

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

All of arXiv

Sunday 27 September

Signal Processing

Robust Transceiver Design for SIM-Assisted Integrated Sensing and Covert Communications

Ahmed M. Benaya, Ali A. Nasir, Khaled M. Rabie et al. (+2 more)

Stacked intelligent metasurfaces (SIMs) have emerged as a promising wave-domain processing technology for sixth-generation integrated sensing and communication networks, reducing reliance on complex radio-frequency hardware. Nevertheless, imperfect channel state information (CSI) can compromise sensing performance and communication reliability. Moreover, ensuring covert transmission introduces a further challenge, as the system must sense potential targets while concealing communication activity from unauthorized wardens. These challenges motivate the development of robust SIM-assisted integrated sensing and covert communication (ISACC) systems. In this paper, we investigate the robust transceiver design of a multi-user, multi-target ISACC system under imperfect CSI. We jointly optimize the transmit and receive beamformers, sensing covariance matrix, and SIM phase shifts to maximize the worst-case minimum sensing signal-to-interference-plus-noise ratio. The formulation enforces constraints on bounded channel uncertainties, user quality-of-service requirements, transmit-power budget, SIM phase shifts, and target detection probabilities. Since the formulated problem is highly non-convex, we develop an alternating optimization framework based on the S-procedure, successive convex approximation, and semidefinite relaxation. Furthermore, to reduce computational complexity, we derive exact lower-dimensional representations of the robust sensing linear matrix inequalities (LMIs) involved in transmit/receive-beamformer designs. We further develop a low-complexity phase-update method that avoids the large sensing LMIs. Numerical results demonstrate that the proposed design outperforms random phase shift and fully digital-beamforming benchmarks, while the low-complexity scheme achieves comparable performance to the LMI-based scheme at substantially lower computational cost.
Read the full abstract

All authors Ahmed M. Benaya, Ali A. Nasir, Khaled M. Rabie, A. Abdelaziz Salem, Daniel B. da Costa

Sound

SCISSOR: Score-Conditioned Instrument Source Separation for Orchestral Recordings

Yiheng Lu and Hao-Wen Dong

Orchestral separation recovers instrument sections from mixtures in which shared pitches, harmonics, and timbres obscure source identity. An aligned score provides instrument labels, note pitches, and activity times. A score-informed approach appends piano rolls to audio features before mask prediction. We introduce SCISSOR (Score-Conditioned Instrument Source Separation for Orchestral Recordings), which uses the score to form a frame-wise query for each source. Each query matches a shared audio representation, and a softmax over instrument and background slots jointly assigns overlapping time-frequency evidence. The queries retain instrument identity even when notes are missing from the score. After training on SynthSOD and a small set of URMP and PHENICX-Anechoic recordings, SCISSOR achieves the highest average SDR on held-out real recordings. With SynthSOD-only training, it leads on SynthSOD and zero-shot PHENICX-Anechoic, and improves on its audio-only control on zero-shot URMP. SCISSOR also degrades less under score corruption than the evaluated score-based baselines.
Read the full abstract

Computer Vision

VehDyn: A Driving World Model Benchmark for Vehicle Dynamics

Tianyi Wang, Wangsheng Du, Jiazhou Chen et al. (+12 more)

Video world models are emerging as data engines, action planners, and generative simulators for autonomous driving, but existing benchmarks primarily assess visual fidelity and coarse physical plausibility, providing limited evidence on whether generated driving futures obey realistic vehicle kinematics and dynamics. This limitation is further compounded by the lack of datasets in which vehicle, road, maneuver, and speed conditions are independently controlled, and ground-truth vehicle states are recorded in synchrony with videos. We introduce VehDyn, a driving world model benchmark for vehicle dynamics. VehDyn is built on a CARLA-CarSim co-simulation platform where photorealistic rendering is coupled with a validated multi-body dynamics model, and it contains 10,080 configurations from a full factorial design over five vehicle types, four tire-road friction coefficients, three maneuvers, four target speeds, 14 scenes, and three illuminations, each paired with synchronized position, velocity, and attitude sequences. Built on this dataset, VehDyn introduces a hierarchical evaluation framework that measures trajectory alignment, kinematic consistency, and dynamic consistency, and benchmarks 12 state-of-the-art video world models. We further assess the video quality using two established protocols and correlate it with the VehDyn score. Trajectory-level metrics are nearly saturated, with ten of twelve models within 20% of ground truth, while no model reaches 92% of ground truth on dynamic consistency, and visual-quality metrics are only weakly correlated with vehicle-dynamics fidelity. DrivingWorld achieves the highest VehDyn score, followed by Cosmos 3 Nano and LTX-Video 2.5, and the VehDyn score agrees closely with human judgment. VehDyn provides a systematic foundation for developing driving world models that are physically consistent and visually realistic.
Read the full abstract

All authors Tianyi Wang, Wangsheng Du, Jiazhou Chen, Tianyi Zeng, Xiangyu Li, Jiseop Byeon, Yujin Wang, Yiming Xu, Yangyang Wang, Bingzhao Gao, Sikai Chen, Zhaomiao Guo, Junfeng Jiao, Christian Claudel, Alexandre Bayen

Probability

Robust Reconstruction on Trees with a Growing Alphabet

Heon Lee

We study robust reconstruction for the \(q\)-state Potts broadcast process on a Galton-Watson tree in the growing-alphabet regime \(q\to\infty\), with boundary depth growing sufficiently quickly in relation to \(q\). We show that, in the regime \(d\lambda >1\), where \(d\) is the expected number of offspring and \(\lambda\) is the nontrivial eigenvalue of the Potts transition matrix, the root posterior is asymptotically unchanged by a broad class of noise channels applied independently to the boundary labels. This remains true even when the probability of retaining the true label at an individual boundary vertex tends to zero as \(q\to\infty\). More precisely, under suitable moment and noise assumptions, the noiseless and noisy root posteriors converge to one another in expected total variation, and hence have the same asymptotic Bayes-optimal reconstruction accuracy.
Read the full abstract

Signal Processing

A Majorization-Minimization Framework for Activity Detection in Mixed Near-and-Far-Field Random Access

Xinjue Wang, Zhi-Yong Wang, Sergiy A. Vorobyov et al. (+3 more)

Grant-free random access in massive machine-type communications requires detecting a small active set from length-L uplink pilots received at an M-antenna base station. Classical covariance-based detectors are largely built on the far-field (FF) model, where the M antenna-domain observations are treated as independent snapshots, and inference reduces to an L $\times$ L covariance description. This model becomes inadequate in mixed near-field (NF) and FF access, where NF devices induce device-specific structured spatial covariances and the aggregate observation no longer fits the FF snapshot structure. In this paper, we develop a unified covariance-aware Rician framework for activity detection that treats FF and NF devices by a single likelihood model. Within this framework, we propose a majorization-minimization projected gradient descent (MM-PGD) detector for the resulting relaxed likelihood. For scalable exact likelihood evaluation, we further derive a Kronecker-Woodbury implementation that exploits the mixed NF/FF covariance structure, and avoids factorizing the full LM $\times$ LM covariance matrix. Numerical results show that MM-PGD is on par with the strongest coordinate-wise baseline in the all-FF limit, while its advantage becomes more pronounced as the fraction of NF users increases under the tested regimes.
Read the full abstract

All authors Xinjue Wang, Zhi-Yong Wang, Sergiy A. Vorobyov, Esa Ollila, Gayan Amarasuriya Aruma Baduge, Mojtaba Vaezi

Computer Vision

EngIntervene: Benchmarking Multimodal Engineering State Understanding and Design Intervention Reasoning

Jinchang Zhang, Yingda Tao, Jiakai Lin et al. (+1 more)

Multimodal engineering benchmarks largely evaluate static understanding, such as recognizing components, interpreting diagrams, or answering technical questions. This leaves a missing middle between engineering perception and full design generation: whether a model can use an understood system state to reason about relations, constraints, and the consequences of design changes. We introduce EngIntervene, a benchmark for this capability. It contains 3,229 questions across seven engineering domains and organizes evaluation into four levels: state grounding (T1), relational and mechanistic reasoning (T2), constraint-aware diagnosis (T3), and intervention reasoning (T4), which asks whether a proposed modification achieves its target while preserving required constraints. The tasks instantiate a unified engineering state representation spanning objects, relations, constraints, and design objectives, and T2–T4 are scored against structured reference answers with atomic criteria. Across open- and closed-weight multimodal models, stronger grounding does not reliably translate into better diagnosis or intervention, and the best open-weight model trails the best closed model by 14.7 percentage points on the T2–T4 average. Removing or shuffling visual evidence consistently degrades performance, while benchmark-specific supervised fine-tuning improves T1 but not T2–T4. T4 further exposes a large gap between satisfying individual revision criteria and producing a fully valid intervention. Engineering reasoning thus requires not only recovering the current state, but also reliably using it to reason about constraints and post-intervention consequences. Code and benchmark artifacts are available at https://github.com/changcv2021/EngIntervene
Read the full abstract

All authors Jinchang Zhang, Yingda Tao, Jiakai Lin, Guoyu Lu

Artificial Intelligence

CORTEX: A Verified Experience Layer for Generalist Agents

Garapati Keerthana and Manik Gupta

An agent can solve a task today and face the same task under new facts, tools, or governing knowledge tomorrow. Most agent systems can retrieve relevant text or recall prior conversations, but they lack a principled way to decide when a previous solution is still valid, when it must be adapted, and when it should be discarded. We introduce CORTEX (Contextual Orchestration and Reuse of Task EXperience), a general AI systems framework that connects specialized agents through an external layer of verified experience. Each episode records its task conditions, source and tool state, decisive predicates, proof trace, verifier, and outcome. A meta-controller chooses exact replay, checked adaptation, fresh synthesis, or escalation. Accepted episodes can become task patterns and procedural strategies through a challenge-driven development loop. This gives the system an implicit competence layer that can grow without changing model weights. We formalize system contracts for exact replay and source-version separation, and derive when reuse saves computation. A controlled two-domain implementation tests the exact-replay core on 1,000 synthetic cases. Complete-family holdouts test procedural transfer on 1,000 new-family cases across eight clinical and policy splits, with complete fresh-evidence grounding and perfect invariance to irrelevant-field and insertion-order perturbations. The transfer trace exposes the work required for verified strategy execution. These results establish an initial path toward general intelligence through reusable procedures, typed experience, and developmental transfer.
Read the full abstract

Machine Learning

GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences

Abdul Monaf Chowdhury, MD Sameer Iqbal Chowdhury, Shifat E Arman et al. (+1 more)

In offline goal-conditioned reinforcement learning (GCRL), divide-and-conquer scales to long horizons by joining two shorter segments at a subgoal. However, under stochastic dynamics, the base case of this rule values the luckiest trajectories through the data. The subgoal must also lie on a shared trajectory, so a state-goal pair that no trajectory connects gets no value update at all. To address both, we present Grounded Transitive RL (GTRL), an offline GCRL value learning algorithm that grounds the divide-and-conquer update with a one-step TD target. Over a single step, TD is correct, as its target averages over the successors and needs no subgoal. GTRL adds this target to the composition rather than replacing it, so every pair receives an update, and the composition still carries the long horizon. GTRL also corrects the bias from hindsight relabeling by reweighting each goal against how reachable it was from other successors. We evaluate our algorithm on nineteen OGBench tasks spanning stochastic, deterministic, and stitching environments, where it achieves the highest average success rate. Code will be released soon.
Read the full abstract

All authors Abdul Monaf Chowdhury, MD Sameer Iqbal Chowdhury, Shifat E Arman, Md Mehedi Hasan

Robotics

PORTER: Edge-Cloud Residency for Persistent 3D Scene Graph Memory

Yue Chang, Yifan Tian, Jiajing Peng et al. (+5 more)

Recent task-driven and just-in-time 3D Scene Graph (3DSG) methods reduce per-task representations by constructing or activating only task-relevant information. Yet sparse per-task working sets do not bound onboard memory usage over a robot's lifetime: as tasks change, payloads accumulated for earlier tasks may become irrelevant to the current task but can be useful again in future tasks. Over repeated task switches and expanding environments, retaining such reusable payloads causes local memory to grow, whereas discarding them entirely can lead to costly repeated construction of the same payloads later. We introduce PORTER, which decouples persistence from residency: lightweight anchors remain in the limited memory of the edge robot while heavy object payloads migrate between the edge and the cloud. Relevance alone is insufficient for deciding residency because multiple relevant payloads may provide redundant information. We therefore decompose each task into functional requirements and introduce Irreplaceable Support Erasure (ISE), which measures the loss in requirement coverage caused by offloading. ISE discounts replaceable support and penalizes losses more strongly when the remaining coverage of a requirement is weak. PORTER constructs a budget-aware local working set by repeatedly offloading the payload with the smallest marginal ISE per byte. Experiments on JITOMA-Bench evaluate PORTER across four 3DSG builders. Under progressive compression, pooled relative mR@3 remains at 100% through 91% payload-byte offloading.
Read the full abstract

All authors Yue Chang, Yifan Tian, Jiajing Peng, Dazhi Huang, Rufeng Chen, Zhaofan Zhang, Li Chen, Sihong Xie

Machine Learning

Two Heads Are Better Than One: Aggregating Weaker LLMs for Better Forecasts

Cheng Peng, Ruixi Luo, Zhi Chen et al. (+1 more)

Large language models (LLMs) are increasingly used to forecast real-world events, but access to the strongest individual forecaster may be costly or otherwise constrained. We study weak-to-strong forecast aggregation: can individually weaker LLM forecasters be aggregated to outperform a stronger forecaster? Using ForecastBench (Karger et al., 2025), we evaluate 70 LLM forecasters across 16 comparison groups, each with more than 1,000 shared subquestions, yielding 1,121 weaker-model pairs. Within each group, we identify the strongest individual by test Brier score and evaluate aggregates composed exclusively of weaker forecasters, with aggregation weights learned on separate training data. We find substantial evidence of weak-to-strong improvement. Learned linear pooling identifies a weaker pair that matches or outperforms the strongest individual in 11 of 16 groups and comes within 5% of its Brier score in all 16 groups. We also find that these improvements do not rely on having a near-best constituent and are generally accompanied by good calibration. Additional analyses show that adding more models does not consistently improve performance, and competitive weaker-model aggregates also remain available under practical constraints.
Read the full abstract

All authors Cheng Peng, Ruixi Luo, Zhi Chen, Wei Tang

Robotics

ActionGround: Training-Free Runtime Refinement of Frozen VLA Policies

Namai Chandra, Madhur Thareja, Shriram Damodaran et al. (+1 more)

Vision-Language-Action (VLA) models map visual observations and language instructions directly to robot actions, but they do not explicitly represent the phase structure of manipulation tasks or the rigid-body dynamics governing execution. We present ActionGround, a neuro-symbolic, training-free runtime layer that wraps a frozen VLA policy without retraining, fine-tuning, or weight access, adding less than 1 ms of overhead per control step. A symbolic phase-aware finite-state machine identifies the manipulation phase (approach, grasp, transport, or place) and applies a phase-specific rule-based correction. In parallel, an always-on, inertia-weighted Euler-Lagrange term incorporates the robot's equations of motion into each control step, while its dynamics residual is logged as a consistency diagnostic rather than used as a gate. We evaluate ActionGround across OpenVLA, OpenVLA-OFT, Force-VLA, and Generalist-VLA on ten LIBERO-Spatial pick-and-place tasks using a 7-DoF Franka Panda. With fixed parameters across tasks and backbones, ActionGround improves success rate by up to 6 percentage points and stability by up to 19.3 percentage points, while improving trajectory efficiency by up to 15%. In a separate Robosuite noise sweep, ActionGround provides approximately a 10x improvement in trajectory-jerk robustness under injected action noise. In a matched-seed Robosuite simulation companion to a real Agilex Piper trial, simulated baseline success increases from 35% to 95%. The physical-hardware experiment is presented as a qualitative deployment demonstration; quantitative per-trial success on the real arm is left for future work. Our evaluation is limited to rigid-object pick-and-place manipulation.
Read the full abstract

All authors Namai Chandra, Madhur Thareja, Shriram Damodaran, Addison Lin Wang

Quantum Physics

NxM-Version Programming for Quantum Software: High-Level Components across Frameworks and Engines

Neilson Carlos Leite Ramalho, Higor Amario de Souza, Anthony Accioly et al. (+2 more)

Quantum computing has in recent years evolved from a purely theoretical field to an active area in both academia and industry. As a result, Quantum Software Engineering has emerged as an area that aims to organize the process of building, testing, and running quantum software. However, writing quantum software still requires programming with quantum gates and qubits, as well as knowledge specific to quantum software frameworks such as Qiskit, Cirq, Qrisp, pyQuil and PennyLane, each of which reaches quantum hardware through its own toolchain. We present Quanifi, which packages the high-level routines of these frameworks as components on the Apache NiFi dataflow canvas. The components exchange circuits as OpenQASM 2.0, so a circuit built by one framework can be executed by another. This allows for two types of redundancy: several frameworks implement the same algorithm, and several engines (simulators or real hardware) execute the same circuit. We describe N$\times$M program execution, which crosses the two: a single NiFi flow runs each of the $N$ implementations on each of the $M$ engines, and because every result is labelled with its implementation and its engine, a disagreement can be linked to an implementation, to an engine, or to a single implementation-engine pair. We ran Grover's algorithm built by three frameworks on three quantum computers from IBM, IQM and Quantum Inspire, and a matrix of three adder builders on one IQM device reached through two routes. N$\times$M execution helped us discover three real defects: an incorrect gate-set declaration in the Quantum Inspire adapter, execution consistent with negated $R_x$ angles on Tuna-17, and circuit modification through Open Quantum. The latter two returned wrong answers without reporting an error. We reported all three defects and Open Quantum's provider confirmed and fixed its QASM parsing defect.
Read the full abstract

All authors Neilson Carlos Leite Ramalho, Higor Amario de Souza, Anthony Accioly, Valter Vieira de Camargo, Marcos Lordello Chaim

Machine Learning

BERT4DTI : BERT-based Model for Predicting Drug-Protein Interactions

Thanina Hamitouch, Khadidja Henni, Abdelkrim Arie et al. (+3 more)

Understanding how drugs interact with protein targets is fundamental to drug discovery, drug repurposing and the early identification of promising therapeutic candidates before costly experimental testing. Sequence-based DTI models face three practical limitations: labelled interactions are scarce and unevenly distributed, large pretrained chemical and protein encoders are expensive to fine-tune end-to-end, and independently encoded sequences do not capture pair-specific dependencies. We present BERT4DTI, which encodes SMILES strings with ChemBERTa and amino-acid sequences with ProtBERT, applies bidirectional mutual attention between token-level representations, and classifies the resulting interaction features using convolutional layers and a multilayer perceptron. To reduce trainable size, ProtBERT is truncated to 18 retained layers and only the last two layers of each encoder are fine-tuned. On BIOSNAP, DAVIS and BindingDB, BERT4DTI is competitive, achieving the best ROC-AUC and PR-AUC on BIOSNAP and the highest sensitivity on all three benchmarks. An ablation on DAVIS shows that mutual attention improves PR-AUC and specificity. With 125M trainable parameters compared with 353M for full BERT fine-tuning, BERT4DTI provides a favourable performance-parameter trade-off for sequence-based DTI screening, while leaving runtime profiling, calibration and leakage-audited validation for future work.
Read the full abstract

All authors Thanina Hamitouch, Khadidja Henni, Abdelkrim Arie, Amina Selma Haichour, Neila Mezghani, Lina Abou-Abbas

Computer Vision

VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis

Kangjie Chen, Xiangyu Li, Dongbin Zhang et al. (+12 more)

We present VGGT-Diff, a geometry-routed multi-view diffusion model for sparse-view novel view synthesis. Existing novel view synthesis (NVS) methods face a fundamental trade-off: reconstruction-based approaches preserve observed geometry but struggle to synthesize unseen regions, while diffusion-based methods provide strong generative priors yet rely on implicit source-to-query correspondence. VGGT-Diff bridges these regimes by routing visual geometry latents from VGGT-{\Omega} into a pretrained video diffusion model. Each visual token is associated with a 3D point and confidence, then transformed into query-aligned latent conditions through a confidence-aware Visual Geometry Router (VGR) that preserves front and back surface evidence. These conditions guide joint target-view denoising, while Point-Track Residual Consistency (PTRC) regularizes predicted-clean residuals along reliable 3D tracks, improving multi-view stability. We further introduce robust geometry conditioning, combining training-time regularization with inference-time guidance for improved robustness. Experiments show competitive or state-of-the-art performance across interpolation and extrapolation under different viewpoint difficulties. Our code is available at https://github.com/chenkangjie1123/VGGT-Diff.
Read the full abstract

All authors Kangjie Chen, Xiangyu Li, Dongbin Zhang, Chaoda Zheng, Shijia Chen, Jinhao Deng, Hongbin Lin, Choo Sin Wai, Minqi Wang, Minghao Yang, Dake Zhong, Guorui Song, Yu Zhang, Xianming Liu, Boyang Wang

Distributed Computing

CascadeEP: Asynchronous Expert Execution for MoE Prefill under Attention Imbalance

Jin Qin, Tiancheng Hu, Shiyan Wang et al. (+12 more)

Mixture-of-experts (MoE) serving commonly deploys data and expert parallelism (DEP): attention replicas run distinct request batches while routed experts are sharded across an expert-parallel (EP) group. During prefill, attention replicas finish dispatch at different times, but synchronous EP delays expert feed-forward network (FFN) computation until routed inputs from all replicas are ready. Request schedulers seek to balance load while reusing the key-value (KV) cache of shared prompt prefixes to avoid redundant prefill computation. These goals can conflict when a replica holding a matching prefix is already overloaded, leaving residual attention imbalance. We present ASYNCEP, a distributed execution engine for MoE prefill. ASYNCEP proposes three mechanisms. Asynchronous EP allows expert computation to start before tokens from all attention replicas are ready. streamFFN batches ready tokens to balance early execution with FFN computation efficiency. Opportunistic expert weight fetching (OEWF) allows a faster replica to fetch expert weights and execute unstarted work from other GPUs. We evaluate ASYNCEP on DeepSeek-V4-Flash, DeepSeek-V4-Pro, and GLM-5.3, and our results show that ASYNCEP achieves up to 1.48x speedup in p95 time-to-first-token (TTFT) and improves the inference throughput by up to 1.17x.
Read the full abstract

All authors Jin Qin, Tiancheng Hu, Shiyan Wang, Junhao Hu, Zexin Jian, Yuzheng Wang, Haoyu Li, Chunwei Xia, Ying Liu, Pixian Zhan, Di Wang, Zhongzhe Hu, Huimin Cui, Tao Xie, Chenxi Wang

Quantum Physics

High-fidelity geometric quantum gates exceeding 99.9% in germanium quantum dots

Yu-Chen Zhou, Rong-Long Ma, Zhenzhen Kong et al. (+11 more)

Achieving high-fidelity and robust qubit manipulations is a crucial requirement for realizing faulttolerant quantum computation. Here, we demonstrate a single-hole spin qubit in a germanium quantum dot and characterize its control fidelity using gate set tomography. The maximum control fidelities reach 97.48%, 99.81%, 99.88% for the I, X/2 and Y /2 gate, respectively. These results reveal that off-resonance noise during consecutive I gates in gate set tomography sequences severely limits qubit performance. Therefore, we introduce geometric quantum computation to realize noiseresilient qubit manipulation. The geometric gate control fidelities remain above 99% across a wide range of Rabi frequencies. The maximum fidelity surpasses 99.9%. Furthermore, the fidelities of geometric X/2 and Y /2 (I) gates exceed 99% even when detuning the microwave frequency by +-2.5 MHz (+-1.2 MHz), highlighting the noise-resilient feature. These results demonstrate that geometric quantum computation is a potential method for achieving high-fidelity qubit manipulation reproducibly in semiconductor quantum computation.
Read the full abstract

All authors Yu-Chen Zhou, Rong-Long Ma, Zhenzhen Kong, Ao-Ran Li, Chengxian Zhang, Xin Zhang, Yang Liu, Hao-Tian Jiang, Zhi-Tao Wu, Gui-Lei Wang, Gang Cao, Guang-Can Guo, Hai-Ou Li, Guo-Ping Guo

Dynamical Systems

No infinite spin in the $n$-body problem in all dimensions

Zhe Wang and Guowei Yu

In the planar $n$-body problem, Moeckel and Montgomery \cite{MM25} showed that there is no infinite spin for total collision solutions, when the reduced and normalized configuration converges to an isolated central configuration. Following their approach, generalizations have been obtained for partial collision solutions and parabolic solutions in the planar case, and for total collision solutions in the spatial cases by various authors, all under the same assumption that the reduced and normalized configuration converges to an isolated central configuration. Here we prove there is no infinite spin for any collision or parabolic solution in all dimensions without such an assumption.
Read the full abstract

Commutative Algebra

Wide subcategories over commutative coherent rings

Tiwei Zhao

In this paper, we mainly prove Hovey's conjecture: for any commutative coherent ring, there is a lattice isomorphism between the lattice of wide subcategories of the category of finitely presented modules and that of thick subcategories of the perfect derived category. We construct, for every finitely presented module, a bounded finite free complex whose zeroth homology is the given module and whose homology lies in its abelian closure. This realization gives an inverse to Hovey's correspondence without a closure operation. In addition, we study finite extension filtrations, their behavior under change of rings, and the limits of reconstructing wide subcategories of arbitrary modules from finitely presented modules.
Read the full abstract

Machine Learning

Feedback-Robust AI for Patient Knowledge Graphs

Mohammed Sameer Syed

Patient knowledge graphs from bedside monitoring should type their relations and state whether the data support their signs. In anesthesia and intensive care, clinicians titrate drugs and ventilation in response to the physiology, so temporal relations mix the patient's response with the clinician's policy. We introduce ClosedLoopBench: 29 relations with signs fixed by physics, pharmacology or clinical practice, on 3,442 VitalDB surgical cases (12,653 h) with negative-control action streams. When each patient's actions are replaced by another patient's, six of 12 estimators declare on average 11-18 of their 19-29 distinct relation estimates significant without calibration, and after calibration cross-correlation and Granger tests still assign ventilator rate -> end-tidal CO2 the sign of the clinician's policy. We propose feedback-robust patient graphs that combine concept nodes with evidence pointers, typed relations admitted against negative controls, and beat-level couplings. On VitalDB under null streams, our graphs contain 0.06-0.10 false concept-level relation instances per graph, versus 10-12 for correlational construction. Patient-specific estimates of 11 slow drug and ventilator responses predict later data no better than population estimates, whereas the pulse-arrival-time-systolic-pressure slope is negative in 94.3% of 2,884 cases and patient-specific (early-late correlation 0.67 [0.63, 0.70]).
Read the full abstract

Statistical Methodology

A Note on Threshold Principle, Artificial Neural Network Connections and Econometric Legacy

Howell Tong

This is mostly a non-technical note, reflecting the author's philosophy and personal views on time series analysis, with references limited to only a few representatives for brevity. The Threshold Principle, formally announced in Tong (1990), modernised time series analysis by introducing a collection of sub-systems to model complex nonlinear dynamics. We explore the conceptual architecture of the Threshold Principle drawing parallels and contrasts with artificial neural network in machine learning. We trace the influential adoption of Threshold Autoregression in econometrics. We examine a smooth extension, namely the smooth threshold autoregression introduced by Chan and Tong (1986) that was later popularized in the Econometric literature. We sound cautions to help econometric users to avoid misuse of this model. Furthermore, we examine how we can systematically apply the Threshold Principle to conditional variance to enable meaningful volatility classification. Finally, we mention some of the modern applications of the Threshold Principle to non-real-valued domains, underscoring its enduring half-century methodological significance as embodied in the threshold autoregression.
Read the full abstract

Machine Learning

Minimax-Optimality of Posterior Sampling for Reinforcement Learning

Taewon Goo and Kihyuk Hong

Posterior sampling for reinforcement learning (PSRL) is one of the simplest and most effective exploration methods, but a basic question has remained open: does unmodified PSRL achieve minimax regret without structural assumptions on the prior? We answer yes. Exact vanilla PSRL is minimax optimal in leading-order Bayesian regret under arbitrary correlated priors. The difficulty is that a posterior-sampled transition model is coupled with its own continuation value. We overcome this with a common empirical transition reference that isolates the resulting value mismatch and a Bellman-based variance argument that controls it without an extra leading-order state-space factor. For finite-horizon, time-inhomogeneous tabular MDPs with unknown stochastic rewards, this yields the minimax $\widetilde{O}(\sqrt{SAH^3K})$ regret rate under arbitrary joint priors over rewards and transitions. The same proof principle gives the minimax $\widetilde{O}(d\sqrt{H^3K})$ rate for linear-mixture MDPs under arbitrary joint parameter priors.
Read the full abstract

Audio and Speech Processing

Acoustic Progress Propagation for Long-Horizon Speculative Decoding in ASR

Yuanyuan Jia and Qianqian Yang

Speculative decoding accelerates autoregressive automatic speech recognition (ASR), but the acceptance length of alignment-aware drafters can saturate as the draft horizon increases. We propose a progress-aware speculative drafter that recurrently propagates an acoustic progress state across draft steps and feeds it back into audio cross-attention to guide token generation. We jointly train the drafter and progress predictor over variable draft horizons. On five ASR test sets, our method achieves lossless, macro-averaged end-to-end speedups of 1.657x and 1.227x over target-only autoregressive decoding with Qwen3-ASR-0.6B and Qwen3-ASR-1.7B, respectively. Relative to AnchorDraft, our method improves the macro-averaged speedup by 34.3% and 9.0%, respectively. Horizon sweeps show continued growth in acceptance length beyond the baselines' saturation. Code is available at https://github.com/yuanyuanjia71-spec/ProgDraft.
Read the full abstract

Artificial Intelligence

ActiveMem: Dynamic Latent Memory Trees for Long-Horizon Agents

Song-Li Wu, Jingyi Wang, Zhaocheng Du et al. (+1 more)

Large Language Model (LLM) agents increasingly rely on external memory to support long-horizon reasoning and decision making. Existing memory systems typically retrieve historical trajectories or summaries as independent context fragments, overlooking the procedural dependencies underlying multi-step execution. As memory scales, such flat retrieval introduces context fragmentation and cross-task interference, leading to structurally inconsistent reasoning trajectories. We propose ActiveMem, a hierarchical memory framework that recursively organizes agent experiences into dependency-aware latent execution trees. ActiveMem abstracts trajectories into reusable subtask nodes while explicitly preserving execution transitions, enabling coherent reasoning-path retrieval conditioned on the current execution state. To support continual adaptation, ActiveMem further learns dynamic memory expansion, retrieval, and pruning policies through reinforcement learning. Experiments across various agent benchmarks demonstrate that ActiveMem consistently improves task completion, reasoning stability, and memory efficiency over existing memory-based agents. Moreover, ActiveMem enables compact open-weight models to achieve competitive performance with substantially larger proprietary systems.
Read the full abstract

All authors Song-Li Wu, Jingyi Wang, Zhaocheng Du, Weinan Gan

Artificial Intelligence

CodeSkill: Latent Skill Abstraction for Long-Horizon Code Agents

Song-Li Wu, Jingyi Wang, Zhaocheng Du et al. (+2 more)

Code agents require long-horizon decision-making over complex interaction trajectories. However, existing reinforcement learning (RL) approaches typically optimize behavior at the token level, creating a mismatch between low-level generation and high-level behavioral reasoning. This limitation leads to inefficient exploration and weak credit assignment under sparse rewards. Moreover, while large-scale agent trajectories often contain recurring multi-step behavioral patterns, their noisy token-level representations hinder effective experience reuse. To address these challenges, we propose CodeSkill, a framework that adapts hierarchical latent skill modeling to the code agent domain. CodeSkill first leverages a teacher model to distill both successful and failed trajectories into multi-level textual abstractions. It then integrates temporal variational inference with reinforcement learning to map these discrete semantics into continuous latent variables, while an adaptive boundary mechanism dynamically gates skill transitions based on execution feedback. The learned skills are injected into a frozen LLM policy as latent semantic prefixes, enabling optimization in a compact semantic space rather than over raw token sequences. By shifting RL from token-level exploration to experience-level reasoning, CodeSkill improves optimization efficiency and long-horizon behavioral coherence. Extensive experiments demonstrate that CodeSkill achieves highly competitive performance against strong open-weight baselines across diverse general and industrial coding benchmarks. Furthermore, the learned skills exhibit strong transferability and robust cross-domain generalization, highlighting the effectiveness of explicit behavioral abstraction for scalable agentic code generation.
Read the full abstract

All authors Song-Li Wu, Jingyi Wang, Zhaocheng Du, Weinan Gan, Weiwen Liu

Functional Analysis

The strong reproducing kernel thesis for Hankel operators and the Garsia norm

Konstantin M. Dyakonov

Given a reproducing kernel Hilbert space $\mathcal H$ and a bounded operator $T$ on $\mathcal H$, we say that $T$ obeys the strong reproducing kernel thesis (SRKT) if $\|T\|=\sup_k\|Tk\|$, where $k$ ranges over the normalized reproducing kernels in $\mathcal H$. Two problems are posed. One of these is to determine which Hankel operators on the Hardy space $H^2$ obey the SRKT. The other concerns the geometry of the unit ball of $BMO$ with respect to the Garsia norm.
Read the full abstract

Analysis of PDEs

Global well-posedness and Decay estimates for solutions of the Navier–Stokes–Maxwell system

Belkacem Said-Houari

We investigate the global solvability and the large-time asymptotic behavior of solutions to the Navier–Stokes–Maxwell system in two and three space dimensions. The system describes the interaction between a viscous incompressible fluid and an electromagnetic field through the Lorenz force and Ohm's law. The system exhibits a parabolic–hyperbolic coupling in which the dissipative Navier–Stokes system interacts with the hyperbolic Maxwell system. The Maxwell system is damped through Ohm's law with the Maxwell correction. For sufficiently small initial data with suitable Sobolev regularity, we establish the global well-posedness of strong solutions and derive optimal decay rates for the solution and its higher-order spatial derivatives. In addition, we show that the electric field decays faster by the extra factor $(1+t)^{-1/2}$ compared to the velocity and magnetic components. One of the key ingredients of our analysis is a detailed study of the linearized system, which reveals refined decay properties of the electromagnetic components. These linear estimates play a crucial role in the analysis of the two-dimensional case, allowing us to overcome the logarithmic loss arising from the borderline decay estimates. For the nonlinear system, our approach is based on a time-weighted energy method, specifically designed to capture the distinct dissipative properties of the fluid and electromagnetic components. A suitable compensating functional is introduced to exploit the coupling between the electric and magnetic fields and thereby recover the missing dissipation of the magnetic field. Combined with careful analysis of the nonlinear terms, these estimates yield our desired result.
Read the full abstract

Machine Learning

The Price of Locality: Why Forward-Forward Underperforms Backpropagation?

Zhaoxian Wu, Haichuan Liu and Tianyi Chen

The Forward-Forward Algorithm (FFA) replaces backpropagation (BP) with layer-wise local contrastive objectives, eliminating the backward pass and the need to retain intermediate activations, yet suffers a persistent performance gap with BP that worsens with depth. This paper diagnoses two structural failure modes: an optimization floor arising from concurrent local updates; and a geometric collapse of layer representations driven by the local update mechanism. On the optimization side, we prove that the FFA loss satisfies the Polyak–Lojasiewicz inequality at each layer; however, simultaneous layer updates induce inter-layer representation-distribution drift, so each layer optimizes against a moving input distribution and incurs an error floor. On the representational side, the pairwise similarity kernel of layer representations contracts exponentially toward rank one as depth increases, collapsing the diversity of per-layer error signals. This collapse bounds FFA's effective learning capacity, which measures the diversity of gradient information across layers, independently of depth, whereas BP's chain-rule signal preserves per-layer diversity, yielding a capacity that scales with depth.
Read the full abstract

Machine Learning (Statistics)

Schrödinger–Föllmer Actor–Critic: Diffusion Policy Improvement with Finite-Sample Analysis

Yuling Jiao, Lican Kang, Jerry Zhijian Yang et al. (+1 more)

Diffusion policies represent multimodal action distributions, but a $Q$-weighted update does not specify how to sample from the resulting target distribution. We propose Schrödinger–Föllmer Actor–Critic (SFAC), an offline-to-online reinforcement learning (RL) method for Kullback–Leibler (KL)-regularized policy improvement through conditional diffusion. A minimax Bellman critic estimates the action-value function, which defines an exponentially tilted target policy. A Doob $h$-transform expresses this update as a correction to the reference diffusion drift. The target drift is a weighted conditional mean of Brownian-bridge labels. We fit it by weighted regression using endpoints from the current policy and pointwise action-value evaluations. In the small-update regime, the KL-regularized update follows the natural policy-gradient direction, and the Doob correction represents the same local change in the space of diffusion drifts. Under suitable conditions, we derive finite-sample bounds that separate the errors from critic estimation, weighted neural drift regression, and diffusion discretization through a reverse-KL actor bound. The average-performance bound depends explicitly on the comparison coefficients over the policy iterations. Across six D4RL offline-to-online tasks, the final scores of the $Q$-guided bridge-regression implementation exceed its offline initialization on every task and Cal-QL on five tasks. We also compare with offline RL and online-only baselines.
Read the full abstract

All authors Yuling Jiao, Lican Kang, Jerry Zhijian Yang, Jincheng Ying

Optimization and Control

Complexity analysis of trust-region methods under $(\alpha,L_0,L_1)$-smoothness

Youssef Diouane, Mohamed L. Habiboullah, Awa Khouna et al. (+1 more)

Generalized smoothness assumptions have attracted growing attention in recent years, motivated in part by machine learning problems in which the gradient of the objective function may not be Lipschitz continuous. Among the most prominent of these is the $(\alpha, L_0, L_1)$-smoothness assumption. Existing methods that attain the best known complexity bounds require knowledge of, or upper bounds on, $\alpha$, $L_0$ and $L_1$, while the few parameter-agnostic methods available do not recover those bounds. In this paper, we show that trust-region methods attain the best known bounds for $(\alpha, L_0, L_1)$-smooth objective functions without prior knowledge of these parameters. Establishing these results requires new analytical tools, beyond those used in classical trust-region complexity analyses. We further show that our working model assumption allows the use of general model Hessian approximations and, in particular, accommodates limited-memory quasi-Newton updates. Finally, we show that our complexity bound is sharp in the nonconvex setting.
Read the full abstract

All authors Youssef Diouane, Mohamed L. Habiboullah, Awa Khouna, Dominique Orban

Robotics

SurgFlow: 3D Object-Centric Contact Flow for Surgical Robot Manipulation

Changwei Chen, Xiao Liang, Yinuo Yang et al. (+6 more)

Paired video-action demonstrations enable autonomous surgical behavior, but such data is scarce: robots perform roughly 1% of surgeries, while video-only data is abundant. Learning 3D object flow offers an embodiment-agnostic way to utilize video data, but flow alone specifies how an object should move, not where and when the tool should engage it, a distinction that is critical in surgery. We introduce SurgFlow, a framework that learns 3D Object-Centric Contact Flow from stereo surgical video without action labels. For each object point, it predicts a future 3D trajectory and contact scores. We extract targets via 3D tracking and tool-object proximity, train a flow matching generator to predict them, and use predicted contact to trigger grasp and release while optimizing end effector motion from flow. On the da Vinci Research Kit (dVRK), SurgFlow succeeds in 37 of 39 stage evaluations across tissue retraction, bimanual reveal, needle pickup, and handover, outperforming baselines trained on equal data with or without action labels. Zero-shot transfer to a humanoid-based laparoscopic robot achieves 85% and 70% average success under similar and novel camera viewpoints, respectively.
Read the full abstract

All authors Changwei Chen, Xiao Liang, Yinuo Yang, Nicole Shen, Peihan Zhang, Sara Wickenhiser, Zekai Liang, Soofiyan Atar, Michael Yip