Computer Vision · Cross-listed from eess.IV
Robust, Estimator-Agnostic Dynamic 3DGS Compression
Chenjunjie Wang, Zixi Huang, Yao Wang et al. (+1 more)
Dynamic 3D Gaussian splats (3DGS) model time-varying scenes using a separate Gaussian set per frame. While neighboring
video frames are highly correlated due to smooth motion, Gaussian representations retain this correlation to varying degrees, depending on whether the
estimator tracks them across time. Some 3DGS compression methods integrate the estimation to exploit temporal redundancy; here, we focus on robust compression regardless of the
estimator. We concatenate groups of frames into one Gaussian set, augment each Gaussian with a frame index, and pass it to a static (i.e., non-temporal) 3DGS codec, converting temporal redundancy into spatial redundancy. Concatenated sets are spatially partitioned to limit
memory. Our technique requires neither a motion model nor knowledge of the training method. Averaged over six N3DV sequences, all six static codecs achieve gains on tracked sets (-42.0% to -71.8% BD-rate) over per-frame coding. On untracked sets, all codecs except HGSC, which appears incompatible with our technique, remain competitive with per-frame coding (-3.5% to +5.0%). We further replace D-FCGS's I-frame coding with our technique while retaining its P-frame coding, yielding an overall BD-rate of -46.2%. We propose to visualize "trackedness" using an inter-frame similarity metric. The project is available at https://wcjj1236.github.io/d3dgs-
benchmark.
Read the full abstract ▾
All authors Chenjunjie Wang, Zixi Huang, Yao Wang, Jona Ballé
Robotics
DynaForge: Planning-Guided Residual Learning for Dynamic Manipulation Demonstration Generation
Yiyang Jin, Yu Zheng, Xiao He et al. (+1 more)
Dynamic object manipulation is essential for
robots operating in real-world environments, yet methods for generating high-quality demonstrations remain limited. Methods designed for static tasks do not readily transfer to dynamic settings. Among dynamic demonstration generators, planning-based methods can fail near contact, while DOMINO-style replay simplifies dynamic interactions and may limit the experience available for policy learning. We present DynaForge, a planning-guided framework that learns residual corrections for dynamic manipulation demonstration generation. DynaForge combines low-frequency global planning with high-frequency object-centric inverse kinematics across task phases, and applies a residual policy to correct actions during dynamic interaction. An implicit curriculum groups rollouts under matched conditions and selects mixed-success groups, focusing residual reinforcement learning on the evolving competence frontier. On Can and Bottle, it uses 0.73x as many optimizer steps as vanilla GRPO at the same nominal environment-step budget, with higher observed final success rates. Across nine simulation tasks, DynaForge increases mean demonstration-generation success from 41.30% of the planning prior to 78.37%. With 800 demonstrations per task, DP3 policies trained on DynaForge data achieve 49.11% mean success, compared with 7.07% for DOMINO data. On three real-world dynamic tasks, DynaForge-trained policies achieve 30-60% success, compared with 0-10% for DOMINO-trained policies, showing the ability of DynaForge for sim-to-real transfer.
Read the full abstract ▾
All authors Yiyang Jin, Yu Zheng, Xiao He, Hesheng Wang
Robotics
PAKT: Physically-Aligned Kinesthetic Teaching for Reinforcement Learning
Lars Johannsmeier and Yashraj Narang
Real-world reinforcement learning (RL) systems still struggle with the demands of contact-rich industrial manipulation, including micrometer-level precision, success rates above 99%, and human-level cycle times. Although off-policy
algorithms can improve performance by leveraging demonstrations and interventions, a key bottleneck is the lack of an intuitive interface for collecting such guidance while complying with constraints of the physical system and the policy. We propose PAKT, a framework for kinesthetic teaching in RL. As opposed to teleoperation approaches, PAKT relies on kinesthetic guidance, which is widely used in industry. However, a critical weakness of kinesthetic guidance is the possibility for the operator to move the
robot along trajectories (e.g., velocities, accelerations, jerk) that the
robot and/or policy cannot physically reproduce. Using PAKT, operators guide the
robot through admittance control, which maps human-applied forces to motion. The downstream reference generator applies the same kinematic limits used during policy execution, keeping the collected trajectories within these limits. To support this teaching interface with an appropriate execution layer, PAKT adds a high-performance control stack that maps low-frequency RL actions to high-frequency torque commands. It consists of a reference generator and subsequent impedance controller, where the reference generator preserves the tracking performance of the impedance controller while improving contact handling and producing smoother policy actions. Across the reported runs on four insertion and industrial assembly
benchmarks, including a data center compute tray, the end-to-end system reduces cycle time by 23%-48% and cumulative intervention count by 62%-86% relative to the HIL-SERL baseline. Project website: https://pakt-website.github.io/pakt-website}{https://pakt-website.github.io/pakt-website
Read the full abstract ▾
Robotics
MachEmbodied-U0: Unified Understanding and Generation Model for Embodied Intelligence
Haoran Wen, Wenfu Wang, Kunsong Shi et al. (+15 more)
General-purpose
robot control requires models to understand task intent, identify where to interact, capture how the scene evolves, and generate precise actions.
Vision-
language-action models provide strong semantic priors but typically do not explicitly model scene dynamics, while world-action models couple visual prediction with control without necessarily exposing the task-relevant semantic and spatial structure needed for fine-grained manipulation. We present MachEmbodied-U0 (ME-U0), a unified
embodied foundation model connecting understanding and generation experts through a Mixture-of-
Transformers architecture. Subtask prediction and affordance grounding guide joint visual-dynamics and action generation via flow matching. Visual dynamics encompass future RGB, depth, surface normals, and optical flow, providing complementary supervision for appearance, geometry, and motion. Multi-rate Rotary Position Encoding (MRPE) aligns visual dynamics with fine-grained control. We pretrain ME-U0 on approximately 4,200 hours of curated demonstrations from robotic
datasets and
egocentric datasets. Using only the supervision natively available in each downstream
benchmark, ME-U0 achieves an average score of 17.66 on the RoboDojo simulation
benchmark and average success rates of 99.0% and 82.5% on LIBERO and LIBERO-Plus, respectively. We additionally validate ME-U0 on real-world robotic manipulation tasks, demonstrating its effectiveness beyond simulation. Without corresponding downstream supervision, ME-U0 further demonstrates zero-shot subtask prediction, affordance grounding, and visual dynamics on simulated and real-world observations. Overall, ME-U0 combines competitive downstream control performance with transferable task-grounding and visual-dynamics capabilities across simulation and the real world.
Read the full abstract ▾
All authors Haoran Wen, Wenfu Wang, Kunsong Shi, Jingke Wang, Wancheng Feng, Yiren Zhang, Yueran Zhao, Xuancheng Zhang, Nanfei Ye, Xingru Chen, Zhaohong Sun, Chengmin Yang, Zikang Yu, Penghao Bi, Jia Shi, Yu Liu, Kun Zhan, Yan Xie
Robotics
From Instrument-Mounted Demonstrations to In-Vivo Execution: Learning Bimanual Laparoscopic Appendectomy Without Robot-Collected Demonstrations
Dongho Yee, Juahn Oh, Jinseok Lee et al. (+10 more)
Most minimally invasive surgery is still performed with hand-held laparoscopic instruments, and the surgeon's instrument kinematics are lost when the operation ends; only the endoscope
video is kept. This paper presents an end-to-end pipeline that captures this motion in the operating room and uses it to train a
surgical robot policy, validated on live animals. We introduce a
surgical instrument-state logger that mounts on the shaft of a standard laparoscopic instrument and recovers its pose and jaw state from an inertial sensor, a time-of-flight sensor and a
Hall sensor, with no external camera or tracker. A data pipeline measures the latency of every sensor channel against a
robot ground truth and aligns the channels before forming observation-action pairs. On these demonstrations we train a
diffusion policy with a fine-tuned DINOv3 backbone, selecting its design by closed-loop rollouts in a physics simulator reconstructed from depth maps of an ex-vivo rabbit appendix. The policy is then retrained on 849 in-vivo demonstrations from four live rabbits and deployed on four additional live rabbits with electrosurgery armed. With the surgeon selecting the
surgical phase, the policy completed the appendectomy in three of the four animals. The results show that demonstrations recorded from a surgeon's own instruments are sufficient to train, select and deploy a bimanual
surgical policy in vivo. The
robot serves only as the timing reference for sensor calibration and as the executor, and collects no demonstrations. Both demonstration corpora are released to support future
surgical robot learning research.
Read the full abstract ▾
All authors Dongho Yee, Juahn Oh, Jinseok Lee, Jiyul Lee, Yechan Seo, Seong Jeong, Minsung Kim, Seonho Shim, Younghoon Noh, Hyuk Choi, Youngbin Kong, Kyu Eun Lee, Hyoun-Joong Kong
Hardware Architecture
Accelerating the Mitigation of LLM Inference Nondeterminism Across GPU Architectures
Liam Cooper, Shinnung Jeong, Hyeran Jeon et al. (+2 more)
Large
language model (LLM) outputs are expected to be reproducible under greedy decoding, yet in practice the same model,
prompt, and software stack produce different outputs on different GPUs. The root cause is floating-point non-associativity combined with hardware-dependent kernel selection. Inference frameworks select different
matrix-multiplication kernels on each architecture, with different parallel reduction orders and unspecified tensor-core arithmetic, and the resulting rounding differences can flip output
tokens. Existing solutions have imperfect cross-architecture reproducibility and incur a significant performance penalty. We present a solution employing a set of fixed-configuration fused-upcast GEMM kernels that load 16-bit weights from
memory, upcast them to FP32 in registers, and accumulate with IEEE-754 arithmetic in a reduction order that is a pure function of the problem shape and is therefore independent of the device, its SM count, or kernel scheduling. By fixing the floating-point reduction order as a function of problem shape alone, every GPU runs the same operation sequence, so cross-architecture reproducibility of the linear layers reduces to correct IEEE-754 arithmetic rather than to rounding differences staying below a tie-flip threshold. We confirm our solution's linear-layer outputs are bitwise identical across NVIDIA Ampere, Ada, and Hopper GPUs, while running $1.17$ to $3.1\times$ faster end-to-end than the state-of-the-art solution and cutting weight-
memory traffic in half.
Read the full abstract ▾
All authors Liam Cooper, Shinnung Jeong, Hyeran Jeon, Jeffrey Young, Hyesoon Kim
Machine Learning
What Should a Self-Teacher See? Privileged Context Design for On-Policy Self-Distillation
Kanghui Tian, Siyuan Liu, Tianxiang Jiang et al. (+8 more)
More privileged information does not always make a better teacher. We study this tension in on-policy self-
distillation (OPSD), where a self-teacher scores the student's own rollouts under privileged context, conventionally a complete reference solution that bundles the final answer with one particular
reasoning path. Holding the student view and training fixed within each scale, we compare that default against three abstractions compiled offline, a named strategy, a method-independent framing, and a problem category, and against an answer-only control that keeps the destination but removes the path. In the primary runs on competition mathematics, the best intermediate contexts improve the in-domain peak mean over the full solution by 1.4 points at 4B and 1.6 at 8B, while storing an order of magnitude fewer hint
tokens. Comparisons across three seeds also show positive mean gains for the framing and category contexts at both scales. Answer-only conditioning remains competitive in the primary runs, within 0.2 points of the full solution at these scales. The preferred context varies with student scale and task. Initial teacher-student KL does not order downstream performance. What a self-teacher should see is therefore not everything it could, but the level of abstraction its student can still act on.
Read the full abstract ▾
All authors Kanghui Tian, Siyuan Liu, Tianxiang Jiang, Shuai Dong, Yizhuo Li, Tian Ding, Yuan Guo, Songze Li, Haowen Hou, Congcong Wang, Yi Wang
Artificial Intelligence
ChatT2: An Adaptive Framework for Developing a Large Language Model-Based Agent for Natural Product Domain Research
Yihan Wang, Qiandi Gao, Yihui Zhuang et al. (+4 more)
Scientific investigations into microbial natural products (NPs) present significant challenges for novices, largely due to the complexity of microbial systems, biochemical diversity, technical skill requirements, and the demands of bioinformatics and data analysis processes. To address these issues, we introduce ChatT2, a large
language model (LLM)-based
agent that is specifically tailored to the unique characteristics of bacterial type II polyketides. These polyketides form a structurally distinct and therapeutically important NP family. ChatT2 was developed within an autonomous multiagent framework composed of a mentor, an executor, and an evaluator, each with defined responsibilities. The mentor acts as an intermediary between ChatT2 and the user, utilizing chain-of-thought prompting to refine the intent of the user. Under the guidance of the mentor, the executor synthesizes
multimodal information via
retrieval-augmented generation techniques and seamlessly integrates bioinformatics and cheminformatics tools. The evaluator ultimately assesses the output of the executor to ensure the richness and accuracy of the retrieved information. Our research highlights how ChatT2, designed with this multiagent framework, addresses the challenges faced by general LLMs in terms of understanding limited, specialized corpora and complex biological information and provides both experts and novices with a valuable tool for exploring various NPs of interest. The ChatT2 webserver can be accessed at https://chatt2.site/#/chat.
Read the full abstract ▾
All authors Yihan Wang, Qiandi Gao, Yihui Zhuang, Liangjun Ge, Heqian Zhang, Jiaquan Huang, Zhiwei Qin
Robotics
Relative Contact Velocity-Controlled Hand-Object Mechanism for Dexterous Tool Manipulation
Sunyu Wang, Jean Oh and Nancy S. Pollard
This work investigates how to enable general multi-finger robotic hands to perform the complete tool manipulation process, which entails picking up a tool, loading it into a suitable pose, and then wielding it. Inspired by human tool manipulation and mechanical design principles, we model the hand and the tool as a unified hand-object mechanism (HOM) composed of sub-assemblies. Specifically, we define a HOM as consisting of the hand, the object, and the generalized contact frames, allowing the HOM's motions to be expressed with the same set of Cartesian-space relative contact velocities, irrespective of the hand's kinematics and geometry. Then, we define a HOM's sub-assemblies as relative contact velocity and contact force constraints between fingers. Building on these definitions, we developed a lightweight and physically interpretable motion planning and contact estimation framework using least squares and a complementary filter. We evaluated our framework in simulation by teleoperating five different robotic hands. The results show that our framework enabled all five hands to execute the complete tool manipulation process, achieving dexterous behaviors even from identical, simple reference trajectories. Furthermore, the results showcase our framework's adaptability to different hands, tools, and tasks, enabled by its kinematic and
geometric foundation. Please visit website for
videos: \href{https://sunyuw.github.io/hom-sim/}{https://sunyuw.github.io/hom-sim/}
Read the full abstract ▾
Artificial Intelligence
Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA
Wenzhi Fang, Nicholas Tzou, Lazar Valkov et al. (+1 more)
Reinforcement learning (RL)-based post-training has become an effective approach for eliciting
reasoning capabilities in large
language models (LLMs). However, adapting post-RL models to new knowledge domains or behaviors through subsequent supervised fine-tuning (SFT) can severely overwrite these capabilities. Existing approaches mitigate such forgetting through experience replay, specialized initialization, or constrained optimization using gradient projection, but either provide limited preservation or incur substantial training overhead. Our analysis shows that
reasoning activations concentrate in low-dimensional subspaces, leaving substantial null-space capacity for adaptation, and that the corresponding approximate null spaces can be reliably estimated from a modest number of examples. Motivated by these observations, we propose Null-Basis Low-Rank Adaptation (NB-LoRA), a parameter-efficient method for adapting post-RL LLMs while preserving their acquired
reasoning ability. We formulate
reasoning retention as a layer-wise hidden-state preservation constraint and construct a fixed approximate null basis from
reasoning activations. LoRA updates are then reparameterized through this basis, enforcing the preservation constraint throughout fine-tuning. Extensive experiments across multiple RL-trained LLMs and diverse downstream tasks show that NB-LoRA matches standard LoRA in adaptation performance, maintains
reasoning accuracy near pre-fine-tuning levels, and generalizes this preservation to held-out
reasoning benchmarks.
Read the full abstract ▾
All authors Wenzhi Fang, Nicholas Tzou, Lazar Valkov, Srinivas Chappidi
Computational Engineering
Hierarchical Multi-Task Learning with Liquidity-Aware Signals for Stock Forecasting
Hengyi Yang, Sida Lin, Yiyan Qi et al. (+4 more)
Stock price
forecasting is a long-standing challenge in computational finance, driven by the inherent randomness of
markets and complex temporal patterns. While recent deep-learning models have raised
forecasting accuracy by jointly modeling inter-stock and temporal price dynamics, they conflate inter-stock relationships with intra-stock temporal dependencies and focus solely on the univariate objective of price movement. To address these limitations, we propose LiMT, a Hierarchical Multi-Task Learning framework that integrates liquidity-aware signals for stock price
forecasting. LiMT employs a
Market Regime Encoder (MRE) module that first extracts contemporaneous cross-stock dependencies, then models each stock's temporal dynamics, yielding a unified latent state. Building on this latent state, we introduce a Liquidity-Driven Learning (LDL) module, a mixture-of-experts architecture that features cross-task gating mechanisms to jointly predict price movement,
volatility, and trading volume. We further design an Adaptive Portfolio Optimization (APO) mechanism that converts multi-task forecasts into executable portfolio weights under transaction-cost and liquidity constraints. Extensive experiments on the CSI300 and CSI500
benchmarks show that LiMT performs best among strong neural and tree-based baselines across the reported metrics. In realistic CSI300 backtests, APO improves annualized return from 3.99% to 10.01% and Sharpe ratio from 1.22 to 1.86 over equal weighting, showing that the multi-task forecasts translate into deployable portfolio gains.
Read the full abstract ▾
All authors Hengyi Yang, Sida Lin, Yiyan Qi, Yankai Chen, Haohan Zhang, Xianhua Peng, Jian Guo
Symbolic Computation
Parallel Integration over Simple Radical Extensions in Mixed Towers: Charlwood's Integrals
Sam Blake
We evaluate a SymPy implementation of the parallel Risch-Norman method using Charlwood's 2008 suite of 50 challenging indefinite integrals. The system automatically builds integrand towers, verifies answers by differentiation, and returns correct, verified integrals for 49 problems with zero errors. The single failure, $\int\arcsin(x\sqrt{1-x^2})\,dx$, is proven non-elementary using a holomorphic-remainder certificate, though limited by an unverified completeness hypothesis on a genus-three curve. Part II's degree bounds successfully reduce classical ansatz sizes by two-thirds without impacting running time. The paper details algorithmic mechanisms like $S'$-units, Pell units, and residue computing in tower coordinates. Compared to mature implementations, this untuned SymPy prototype is slower than FriCAS (by a factor of six on the median integral) but more accurate than AXIOM (which returned three wrong answers). Profiling pinpoints performance bottlenecks in nonlinear norm searches and nested number fields, outlining clear targets for optimisation.
Read the full abstract ▾
Computer Vision
Evidence-gated multimodal parsing and vectorization of architectural floor plans
Hongxuan Chen, Wenda Wang, Jiachen Lu et al. (+5 more)
Architectural floor plans remain a high-friction barrier to archive digitization and early design-model preparation because heterogeneous graphics encode spatial semantics and editable geometry together. We introduce SALI-FP, an evidence-gated
multimodal pipeline that converts a plan into reviewable semantic maps, objects, vectors, and relation records while constraining local revisions by image evidence. In a full production audit of 11,534 heterogeneous plans, SALI-FP produced structured outputs for every plan, including 752,510 valid polygon-bearing objects. The same output form has supported initial drawing digitization and design-model preparation in practical design work. Public-
benchmark calibration is paired with a 30-case matched visual evidence set in Appendix F, where room-scale coverage, openings, oblique boundaries, and circulation continuity can be inspected directly. SALI-FP offers an engineering-oriented interpretation-to-geometry workflow for reviewed CAD/BIM preparation and existing-building information recovery.
Read the full abstract ▾
All authors Hongxuan Chen, Wenda Wang, Jiachen Lu, Qirui Shen, Zilong Huang, Lei He, Xinyue Dong, Weixin Huang
Robotics
A Deployable Four-Finger Payload for Teleoperated Free-Flying Manipulation with Astrobee
William Su, Jordan Kam, Yunosuke Nakamura et al. (+3 more)
This article presents a bimanual teleoperation pipeline and conceptual design of a deployable four-finger payload for intra-vehicular free-flyers. Future habitats in low-Earth orbit (LEO) will require systems to perform mundane tasks like cargo handling and maintenance during crewed and uncrewed periods. The gripper payload provides 17 manipulation degrees-of-freedom (DoF) through four independently actuated fingers on a linear rail system. To control it, a virtual reality (VR) device interface maps the human ground operator's hand motions to the finger pairs, their separation to the rail, and common wrist motion to Astrobee translation. We present the preliminary results of teleoperating Astrobee in a custom zero-
gravity MuJoCo-based International Space Station (ISS) simulator through ten repeated trials of transporting a rigid ISS Cargo Transfer Bag (CTB). We measure task success, continuous contact retention, completion time, and cargo motion.
Read the full abstract ▾
All authors William Su, Jordan Kam, Yunosuke Nakamura, Yixiao Wang, Jianshu Zhou, Masayoshi Tomizuka
Human-Computer Interaction
SurgGaze: Implicit Calibration for Accurate Gaze Analysis in Operating Rooms with Wearable Eyetrackers
Jingying Wang, Rosiana Natalie, Keyuan Hu et al. (+5 more)
Accurate gaze tracking is essential for understanding surgeons' visual
attention and cognitive processes during laparoscopic surgery, yet wearable eye trackers produce large errors systematically correlated with ground-truth gaze locations, as demonstrated in Study 1. We introduce SurgGaze, an implicit calibration method that corrects these errors using high-confidence
surgical moments. Building on evidence that surgeons' gaze converges near the tool-tissue contact point (TTCP) during dissection, SurgGaze uses TTCP as a surrogate for true gaze to construct training pairs. We evaluate SurgGaze in a simulated operating room trial and an authentic operating room case study. In simulation, SurgGaze reduced gaze estimation error by 40.6%, significantly outperforming conventional 9-point explicit calibration. The case study showed that these moments provide reliable training data and that calibrated gaze improves interpretation of surgeons'
attention beyond numeric error reduction. These findings demonstrate that structured behavioral signals can enable implicit calibration for gaze tracking in complex real-world settings.
Read the full abstract ▾
All authors Jingying Wang, Rosiana Natalie, Keyuan Hu, Wenqian Xu, Brian George, Vitaliy Popov, Anhong Guo, Xu Wang
Computation and Language
Qwen3.8-Omni: Towards Native Omni-Modal Agents
Qwen Team
We introduce Qwen3.8-Omni-Flash, a natively
multimodal agentic model for real-world
multimodal productivity. Compared with previous omni models, which primarily emphasized perception and interaction, Qwen3.8-Omni-Flash substantially improves
multimodal understanding and
reasoning, as well as performance on long-horizon agentic tasks. These capabilities are supported by a native
multimodal co-training strategy that preserves strong text-domain capabilities while facilitating the transfer of agentic capabilities from text to audio and
video tasks. The model inherits the sparse mixture-of-experts (MoE) architecture of Qwen3.8-Next and extends the context window to one million
tokens, supporting long-context
multimodal reasoning and long-horizon planning. These advances enable integration into production workflows as a primary
agent or a specialized sub-
agent, supporting
video editing, long-form audio and
video translation, music-conditioned music
video or movie generation, and
video-based note or omni-skill creation. To address the lack of native audio and
video support in existing
agent harnesses, we release Qwen-MM-Plugins, a lightweight open-source plugin framework for
multimodal productivity. We further frame real-time
multimodal interaction as a system-level challenge requiring orchestration of context and
memory management, tool use, and sub-
agent delegation. Accordingly, we release Qwen-Live-Harness, an open-source framework for building responsive, real-time
multimodal agents based on Qwen3.8-Omni-Flash. Extensive evaluations demonstrate that Qwen3.8-Omni-Flash achieves strong performance across
multimodal understanding,
reasoning, long-horizon agentic execution, and
video productivity tasks. These results and the accompanying open-source tools support Qwen3.8-Omni-Flash as a practical foundation for deploying natively
multimodal agents in research and production.
Read the full abstract ▾
Sound · Cross-listed from eess.AS
SRF-SVB: Style-Consistent Singing Voice Beautifying via Rectified Flow
Wenhui Li, Biao Dong, Liwei Hu et al. (+2 more)
Singing voice beautifying (SVB) aims to correct pitch and rhythm of amateur singing while enhancing vocal quality, preserving lyrics and the singer's timbre. Existing methods, however, suffer from limited generation quality and efficiency, and tend to neglect the preservation of the singer's style. We propose SRF-SVB, a style-consistent model for SVB via rectified flow, which achieves high-fidelity and efficient beautification covering pitch and rhythm correction. Furthermore, we design a context-guided masked mel-spectrogram inpainting mechanism that effectively preserves the amateur singer's style, including unique timbre and expressive patterns. Experiments on both English and Chinese test sets show that SRF-SVB outperforms baseline models in most objective and subjective metrics.
Read the full abstract ▾
All authors Wenhui Li, Biao Dong, Liwei Hu, Jiqing Han, Yongjun He
Artificial Intelligence
ArticleMiner: Ontology-Guided Knowledge Graph Construction from Scientific Publications
Md Abrar Jahin, Craig A. Knoblock and Jay Pujara
Scientific papers keep much of their quantitative content in tables and supplementary files, where a number means something only through its header, caption, unit, analytical method, and the conventions of its field. Recovering the rows and columns of a table is therefore not the same as recovering the scientific fact it reports. Most semantic table-interpretation methods assume that a clean table is already available and subsequently map its
cells or columns to ontology terms, whereas most publication-level extraction systems are designed for a single domain. We study a middle path: a shared process that reads a paper and its supplementary files, gathers evidence from several parsers and a
language model, and reconciles that evidence, while a bounded human-authored task module for each task supplies the domain meaning. The module lists the canonical names the graph may use, the surface forms that map to them, a small set of derivation rules and validity constraints, an identity key, and the bindings used to write RDF. It defines what a task is allowed to emit; it does not try to list every convention of a field. We build four such modules (for drug-discovery chemistry, materials science, machine learning, and mineral geochemistry) in the ArticleMiner framework, and evaluate them on 163 papers, including a new geochemistry
benchmark with expert-curated ground truth. In comparisons against a same-LLM few-shot baseline, the point estimates favor ArticleMiner on all four tasks, with uncertainty on the two smaller
benchmarks. The geochemistry comparison also includes access to supplementary files, so its improvement cannot be attributed to domain guidance alone.
Read the full abstract ▾
Robotics
CableVLA: Simulation-Privileged Global-Local Representation Learning for Cable Routing
Zhifei Teng, Bo Feng, Xiang Zou et al. (+4 more)
Cable routing requires coordinated control of global cable
topology and changing local contacts. We present CableVLA, an end-to-end
multimodal vision-
language-action framework that converts simulation-privileged supervision into deployable cable-
topology and tactile representations. TopoHead distills node-level physics and current and future cable-
topology information into causal visual context for the action expert. TacSense uses complementary frame and taxel branches to learn contact dynamics from resistive arrays, with simulator-derived kinematics and contact events providing supervision beyond the measured force map. A contact gate activates force-tactile residuals that refine the next 8 arm-and-gripper actions of a frozen
topology-conditioned policy. Across 345 MuJoCo evaluations, CableVLA improves success from 62.6% for the $\pi_{0.5}$-V visual baseline to 84.9%. TacSense achieves pronounced gains in slip-transition recognition over a CNN-LSTM baseline with a similar parameter count, and this advantage persists under frozen-encoder probes.
Topology prediction and 57-task tactile evaluations assess representation quality, while policy adaptation studies evaluate downstream control performance. Cross-simulator and real-
robot comparisons further examine zero-shot policy transfer under changes in dynamics and sensing.
Read the full abstract ▾
All authors Zhifei Teng, Bo Feng, Xiang Zou, Jinpeng Xiao, Min Li, Zhouping Yin, Yiqun Li
Machine Learning · Cross-listed from stat.ML
Generalized Deep Regression for Repeated Measurements
Kexuan Li
In this paper, we study the estimation of a marginal regression function from independent units with repeated binary, count, or continuous responses using ReLU deep neural networks. In the model, we assume that the dependence is generated by an unobserved random mean function within each unit. We then fit a neural network with a convex generalized regression loss. We show an oracle inequality by separating conditional measurement variation from between-unit variation. In addition, we prove that with $n$ units and $m$ measurements per unit, ReLU networks can attain an integrated mean squared error of order $n^{-1}+(nm)^{-2\beta/(2\beta+d)}$, up to logarithmic factors, over $\beta$-Hölder classes. We also derive a weighted oracle inequality for unequal cluster sizes and a rate for compositionally smooth functions. For pointwise ensemble inference, we give a projection central limit
theorem and prove infinitesimal jackknife consistency under an explicit asymptotic linearity condition. Simulations and real data examples are provided to support our theoretical findings and practical implications.
Read the full abstract ▾
Computer Vision
Ultra-fast Neural Inference for Stochastic Gaussian Splatting Denoising
Chenxiao Hu, Hao Zhang, Yanchen Zhang et al. (+3 more)
Stochastic rendering eliminates the sorting and alpha blending process in Gaussian splatting, at the cost of introducing spatial noise. Formulating temporal denoising over the pixel stream shared by view-consistent
stochastic splatting renderers, we propose a temporal neural denoiser validated on
stochastic 2D Gaussian Splatting rendering, combining dual-path exponential moving average accumulation, per-pixel learned trust prediction for history validation, a fixed anisotropic spatial filter and a variance-gated composition with stabilization. The denoiser suppresses the noise, achieving temporally stable, visually compelling outputs during free camera
navigation, all while retaining the sort-free, blend-free rasterization performance. The combined pipeline retains a PSNR gap to sorted alpha-blending renderers, but the denoiser's overhead stays below the time saved by removing sorting and blending.
Read the full abstract ▾
All authors Chenxiao Hu, Hao Zhang, Yanchen Zhang, Meng Gai, Guoping Wang, Sheng Li
Formal Languages and Automata
Testing and Learning Symbolic Finite State Machines
Wen-ling Huang and Jan Peleska
Symbolic finite state machines (SFSMs) describe input/output behaviour using guards and output assignments with possibly infinite data domains. We study deterministic and completely specified SFSMs whose guards and output assignments depend only on the current input. We define finite representative input sets that contain witnesses for relevant guard overlaps and separating witnesses for output assignments that differ on those overlaps. Our main
theorem shows that
language equivalence of the finite instantiations implies
language equivalence over the full input domain. This result transfers complete testing methods for deterministic finite state machines (DFSMs) to SFSMs, provided finite sets of admissible guards and output assignments and an upper bound on the number of distinguishable reachable states are known. Under these assumptions, a DFSM learner with complete testing can learn a finite instantiation, which is then lifted to an equivalent SFSM. We establish a bound on the size of representative input sets and give an SMT construction whose correctness and termination hold under stated solver assumptions.
Read the full abstract ▾
Machine Learning
Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs
Shubham Santosh Pandere, Gautam Ranka, Ritika Varshney et al. (+3 more)
In
language models, the choice between believing the
prompt and believing the weights is made by a handful of identifiable
attention heads. Instruction tuning changes how models behave under conflict, but whether it rewires the underlying
circuit or merely gates/reweights already present components, remains unknown. We provide the first mechanistic base-vs-instruct comparison of conflict-resolution
circuits, across three families (Llama-3.2-3B, Qwen-2.5-3B, Gemma-3-4B). Five independent methods, node and edge attribution, superposition role analysis, causal ablation, and path patching, converge on gating, with the same heads, in the same late-layers, are found to be reweighted rather than replaced with a high node overlap (0.60-0.82). Behaviorally, tuning shifts models toward parametric
memory, making instruct models reject a terse counterfactual context far more than base ones, the opposite of a naive user-following expectation. Yet this added skepticism is a factor of framing since it disappears when the same false claim is delivered as a coherent, evidential passage. The robustness that instruction tuning buys against terse injection is therefore real but narrow. More broadly, we believe that because the conflict
circuit is preserved rather than rebuilt, interpretability and control tools calibrated on base models should transfer directly to their deployed instruct siblings.
Read the full abstract ▾
All authors Shubham Santosh Pandere, Gautam Ranka, Ritika Varshney, Navya Deshmukh, Roushni Sareen, Roshan Kumar Singh
Computer Vision
Observer Choice and Threshold Selection in Retinal Vessel Segmentation: A Subject-Separated Evaluation
Wenhao Xu, Yixian Kong, Ting Pan et al. (+2 more)
The annotation used to select a
segmentation threshold is part of the evaluation protocol, yet its effect is easily conflated with model quality. We examine this choice for retinal vessel
segmentation using all 28 CHASE DB1 images and both human annotations. A fixed seven-fold protocol keeps both eyes of each of the 14 subjects together. Random forests and Extra Trees are fitted against observer 1 with three random seeds, yielding 42 fits. Five threshold policies share identical score maps: fixed 0.50, observer-1 tuning, observer-2 tuning, mean-observer tuning, and maximin tuning of the per-image lower observer Dice. For random forests, maximin changes the threshold in 19 of 21 fits, but worst-observer Dice decreases from 70.53 percent to 70.45 percent. The paired difference is -0.073 percentage points, with a conditional subject-bootstrap 95 percent interval of [-0.384, 0.238]. Extra Trees shows the same direction. Identical observer-1-tuned random-forest masks score 73.66 percent against observer 1 and 71.06 percent against observer 2. The results support explicit reporting of both the threshold-selection reference and evaluation reference; they do not support an accuracy benefit from maximin tuning in this cohort. All splits, raw predictions, metrics and code are supplied. AI assistance is disclosed.
Read the full abstract ▾
All authors Wenhao Xu, Yixian Kong, Ting Pan, Feilong Wang, Changwei Wang
Systems and Control
Optimal Operation Method for Computing Power-Electric Power Coordination Considering End-to-End Completion Latency of Computing Tasks
Yize Liu, Mingyu Yan, Jianfeng Wen et al. (+3 more)
With the rapid growth of computing demand and the large-scale integration of renewable energy, how to realize the coordinated optimal operation of computing networks and power networks has become an important issue to be addressed. However, existing studies mainly focus on the impacts of spatiotemporal migration of computing loads on power system operation, while the internal task processing procedures of computing networks are largely neglected. To address this issue, this paper proposes an optimal operation method for computing power-electric power coordination considering the end-to-end completion latency of computing tasks. First, a full-process latency model covering the "transmission-buffering-computation" procedure of computing tasks is established, which uniformly characterizes forwarding waiting, network transmission, queueing, and computation processing. Second, a task-level spatiotemporal scheduling mechanism is developed to jointly optimize the task forwarding time, routing path, and destination computing node. Then, a computing power-electric power coordinated optimization model is formulated to minimize the power supply cost of the power network and the total completion latency of computing tasks. Case studies demonstrate that the proposed method can fully exploit the task-level spatiotemporal scheduling flexibility of computing loads and facilitate the spatiotemporal matching between computing loads and renewable energy, thereby reducing the system power supply cost while ensuring the quality of service for computing tasks.
Read the full abstract ▾
All authors Yize Liu, Mingyu Yan, Jianfeng Wen, Meng Song, Qing Yang, Mariusz Malinowski
Artificial Intelligence
Evaluating Coding Agents on Kernel Exploit Generation
Junyoung Jang, Gwanhyun Lee, Hwiwon Lee et al. (+4 more)
Coding
agents now find real vulnerabilities in production software. However, bug discovery results do not measure whether
agents can construct exploit primitives. We introduce KEX-bench, a
benchmark for evaluating coding
agents on exploit primitive generation against real operating-system kernels. KEX-bench contains 45 task instances across 40 Linux and Windows CVEs, covering kernel address leak, instruction-pointer control, heap read, heap write, and arbitrary address write. Each task runs in an isolated virtual machine, exposes controlled tools, and uses a deterministic verifier to check primitive-specific success. We evaluate state-of-the-art coding
agents paired with frontier and open-weight models under fixed tool-call budgets. Without a reference proof of concept (PoC), the strongest configuration solves 1 of 20 Windows tasks (5.0%) and 14 of 25 Linux tasks (56.0%). With a reference PoC, the strongest configuration solves 31 of 45 tasks (68.9%). This highlights the gap where
agents reach kernel crashes but fail to shape kernel state into exploit primitives. We release KEX-bench for reproducible research on AI-assisted exploitation at https://kex-bench.github.io.
Read the full abstract ▾
All authors Junyoung Jang, Gwanhyun Lee, Hwiwon Lee, Kyuheon Kim, Jongseong Kim, Jinho Jung, Lingming Zhang
Information Theory
The ISAC Tradeoff Cliff: Fundamental Limits under Waveform Uncertainty and Finite Blocklength
Mohammed Zafar Ali Khan and Lajos Hanzo
Integrated Sensing and Communication (
ISAC) enables the joint design of communication and sensing functionalities using a shared waveform, but its performance critically depends on the accuracy of the transmitted signal available at the sensing receiver. In practical systems, this signal is obtained by finite blocklength decoding . This paper develops an analytical framework for quantifying the impact of the associated decoding uncertainty on sensing performance. We model decoding errors via an equivalent noise formulation that captures their second-order effect on the sensing receiver, and derive the corresponding Fisher Information and Cramér–Rao Bound (CRB). The resultant characterization reveals a fundamental sensing–communication tradeoff governed by the communication rate and decoding reliability. This shows that the classical finite blocklength reliability results in a fundamentally new insight concerning
ISAC systems: when the decoded communication waveforms are reused as sensing references in a data-aided fashion, the communication reliability boundary also acts as a sensing-information bound. {We identify and characterize a sharp transition in sensing performance – referred to as the Tradeoff Cliff – arising from finite blocklength reliability effects.} This transition separates the regimes of near-ideal sensing performance from those of excessive estimation error as the communication rate approaches capacity. Furthermore, we provide an explicit expression for the critical rate at which this transition occurs, showing its dependence on blocklength, channel dispersion, and target error probability. Monte Carlo simulations under both AWGN and block fading channels validate the theoretical analysis and confirm the trend observed. The results provide design insights for operating
ISAC systems with an appropriate reliability margin to avoid severe sensing degradation.
Read the full abstract ▾
Artificial Intelligence
Transformer Heads Looking for Order
Jasper van Doornmalen, Alexander Kozachinskiy, Corinna Mathwieser et al. (+4 more)
In this note, we show that the problem of checking, whether a sequence of bits is ordered, is not doable by 1-head 1-layer
transformers but is doable by a 2-head 1-layer
transformer. Unlike similar previous results, our results assume the model where
transformers have an output MLP.
Read the full abstract ▾
All authors Jasper van Doornmalen, Alexander Kozachinskiy, Corinna Mathwieser, Tomasz Steifer, Felipe Urrutia, José Verschae, Przemysław Andrzej Wałȩga
Software Engineering
Understanding Maintenance and Support in a Community-Driven Scientific Workflow Ecosystem: A Cross-Space Study of Galaxy
Khairul Alam, Kowsik Roy, Md Shamimur Rahman et al. (+1 more)
Galaxy is a widely used, community-driven scientific workflow system whose sustainability depends on continuous maintenance across its software, tools, workflows, infrastructure, documentation, and user-support ecosystem. However, maintenance knowledge in
Galaxy is distributed across development and community-support spaces, making it difficult to understand what is maintained, how maintenance artifacts are resolved, and how user-facing concerns connect to repository-level development. We conduct a large-scale empirical study of
Galaxy using 11,762 GitHub issues, 52,203 pull requests, and 6,235 Community Forum discussions. We characterize maintenance and support concerns, examine factors associated with resolution outcomes and resolution time, and investigate explicit and candidate connections among maintenance artifacts across these spaces. Using BERTopic modeling, we identify nine issue topics, 14 pull-request topics, and 14 forum topics, revealing a maintenance landscape spanning workflow execution, data management, tools and dependencies, infrastructure, testing, scientific resources, documentation, and user support. Resolution analyses show that coordination, diagnostic, contributor, automation, and engagement characteristics exhibit different associations with whether artifacts are resolved and how quickly resolution occurs. We further find limited explicit traceability between development and support spaces: 97.77% of 16,426 resolved explicit relationships occur within GitHub, while only 294 connect GitHub artifacts with Community Forum discussions, despite additional semantic and technical relatedness across these spaces. Together, these findings characterize
Galaxy maintenance as a distributed ecosystem-level process and identify opportunities to improve diagnostic reporting, lifecycle-aware triage, cross-space traceability, and the reuse of community-support knowledge.
Read the full abstract ▾
All authors Khairul Alam, Kowsik Roy, Md Shamimur Rahman, Banani Roy
Human-Computer Interaction
Deflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus
Hasibur Rahman, Malak Sadek and Smit Desai
Large
language models increasingly support decisions where values are in tension, yet little is known about whether interacting with them changes which values users prioritize. In a preregistered study, 200 U.S. adults interacted with ChatGPT, Claude, or Gemini as a thinking partner or read fixed AI-generated considerations. The
prompt asked LLMs to support
reasoning without recommending a decision and named no values. Participants advised people facing real dilemmas and completed parallel PVQ-RR forms before, immediately after, and one task later. Each LLM condition temporarily shifted value priorities toward personal focus relative to the control (d=0.37-0.51), primarily through increased Self-Enhancement. Participants' advice retained words and meaning from their exchanges. Thus, a brief LLM interaction that neither targets values nor seeks to persuade can reorient values active during judgment without detectable convergence in value directions or advice.
Read the full abstract ▾