Hardware Architecture
"Is Low Power Enough?" Rethinking Energy Efficiency in High-Fidelity Sensing
Chae Young Lee, Lan Mei, Jesse Fonseca et al. (+1 more)
For two decades, long-lived sensor nodes have been built from the lowest-power parts, because their scalar readings take only milliseconds to acquire and send. Scientists now want higher fidelity data from the field, such as images and audio, and these observations break that rule: a low-power microcontroller stays awake for seconds to read, store, and transmit each one, so low power is no longer low energy. We argue that long-lived, high-fidelity nodes should instead be built around a more capable microcontroller, provided the whole board sleeps deeply. We revisit two principles from early sensor networks, "race to sleep" and "talk less", for high-fidelity data and on-device AI, and test them by comparing the STM32N6, which pairs a fast core with a neural accelerator, against the low-power Apollo4 Plus. Although the STM32N6 draws 1.9x more power, it completes an observation (capture, storage, on-board detection, and a LoRa transmission) 9.9x faster and so uses 5.2x less energy. On the same model, it runs inference with 3.2-11.4x less energy, and it fits models over 23 points more accurate. A high-fidelity node lives longest when it finishes quickly, sleeps deeply, and sends only what matters.
Read the full abstract ▾
All authors Chae Young Lee, Lan Mei, Jesse Fonseca, Zerina Kapetanovic
Computer Vision
PixARG: Pixel-Asynchronous Retrieval-Augmented Diffusion for Fast and Realistic Image Generation
Zewei Xin, Qinya Li, Chaoyue Niu et al. (+1 more)
While
diffusion models achieve impressive image generation capabilities, they suffer from high computational costs, implausible artifacts, and limited adaptability to dynamic or private data due to static, centralized training. To address these, we propose PixARG, a novel
retrieval-augmented generative framework that integrates dynamic real-world image
retrieval into the
diffusion pipeline to simultaneously enhance efficiency and visual realism. Specifically, PixARG constructs a pixel-level affinity map between the user's text
prompt and the retrieved image to guide a heterogeneous noise initialization. By modulating noise intensity across spatial regions, this mechanism preserves semantically relevant structural priors while perturbing less relevant areas, thereby significantly accelerating convergence. To accommodate this spatially non-uniform noise and ensure synchronized generation, we introduce a pixel-wise asynchronous denoising scheduler and a spatiotemporal denoiser conditioned on the affinity map. Furthermore, we derive an affinity-adaptive training objective that elegantly balances deterministic restoration with
stochastic regeneration across pixels. Experiments on LAION and COYO
datasets across offline, online, and user-specific settings show PixARG enhances realism and semantic
alignment while drastically reducing
diffusion steps.
Read the full abstract ▾
All authors Zewei Xin, Qinya Li, Chaoyue Niu, Fan Wu
Combinatorics
Induced-Count Discrepancy in Uniform Hypergraphs
Chenglong Yu
Let $u_k^{(r)}(H,p)$ be the maximum, over all $k$-vertex $r$-uniform hypergraphs $F$, of the absolute difference between the number of induced copies of $F$ in $H$ and its expectation in the binomial random $r$-graph with the same number of vertices as $H$ and edge probability $p$. Let $u_k^{(r)}(n,p)$ be the minimum of $u_k^{(r)}(H,p)$ over all $n$-vertex $r$-uniform hypergraphs, and let $D_r(n,p)$ be the distance from $p\binom nr$ to the nearest integer. For fixed $r\ge3$, $k\ge2r$ and $\varepsilon>0$, the quantity $u_k^{(r)}(n,p)$ has order $\max\!\left\{D_r(n,p),p(1-p)\right\}n^{k-r}$ whenever $p(1-p)n^{\lfloor r/2\rfloor/(\binom{2r-2}{r}-1)}\ge\varepsilon$. Using local moment estimates and switchings in a sparse reservoir, we construct one hypergraph with the nearest-integer edge count that controls all induced orders simultaneously.
Read the full abstract ▾
Operator Algebras
C*-algebras of Essentially Tracially Rank One
Huaxin Lin
We introduce the notion of essential tracial rank at most one for simple $C^*$-
algebras. We show that separable simple $C^*$-
algebras with essential tracial rank at most one have several regularity properties, including stable rank one, strict comparison, and tracial approximate divisibility. A finite amenable simple $C^*$-
algebras with this property is $\mathcal Z$-stable. We also prove the converse. Thus this property gives a new characterization of separable simple finite amenable $\mathcal Z$-stable $C^*$-
algebras and shows that these
algebras admit a one-dimensional tracial approximation. In the unital real-rank-zero case, this approximation can be strengthened to show that the
algebra has tracial rank zero. This completes a long-standing project. As a byproduct, we prove that every tracial state on a unital separable simple finite amenable $C^*$-
algebra is quasidiagonal and that the
algebra itself is quasidiagonal. Consequently, every separable simple finite amenable $C^*$-
algebra of finite
nuclear dimension has finite decomposition rank. None of these results requires the UCT.
Read the full abstract ▾
Machine Learning
DeKoR: Decomposed Knowledge Routing for Efficient GNN–LLM Fusion
Peiyuan Li, Yongqi Huang, Jitao Zhao et al. (+2 more)
Large
Language Models (LLMs) have shown strong potential for text-attributed graph learning by leveraging rich pre-trained knowledge and
language understanding capabilities. Combining LLMs with Graph Neural Networks (GNNs) offers a promising paradigm for expanding the modeling capabilities of graph learning. However, LLMs and GNNs follow distinct learning paradigms, leading to a pronounced mismatch between their knowledge spaces. Such discrepancies make effective knowledge fusion nontrivial. Moreover, existing methods often incur substantial additional computation for only limited performance gains. To address these challenges, we propose DeKoR, an efficient framework for GNN and LLM knowledge fusion. To enable efficient knowledge transfer, DeKoR decomposes LLM knowledge into complementary local and global views and uses the LLM as an offline teacher to distill them into lightweight experts. To enable selective knowledge fusion, an adaptive router learns how much each node should rely on each expert. Extensive experiments on multiple
benchmarks demonstrate that DeKoR outperforms existing baselines on both node and subgraph classification, achieving superior effectiveness and efficiency.
Read the full abstract ▾
All authors Peiyuan Li, Yongqi Huang, Jitao Zhao, Di Jin, Dongxiao He
Computation and Language
Vela: User Behavior as Supervision Sparks LLM Intelligence
Yang Xiao, Yusong Sun, Haoyi Wu et al. (+17 more)
Large
language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommendation and advertising systems. These applications demand the user dimension of LLM intelligence: inferring a person's preferences, intent, and likely future actions from weeks to years of behavior data. Yet current models are trained on static text or synthetic data, neither of which captures how user behavior evolves over time. Real-world behavior records, already available at scale on content platforms and in personal-assistant
agents, offer a natural supervisory signal. We propose user behavior as supervision and introduce Vela, a framework that converts real user behavior data into trainable tasks and trajectories. From the anonymized behavior records of 100,000 users, Vela generates 100,000 tasks across 91 real-world task templates; difficulty-based filtering and trajectory acceptance criteria retain approximately 75,000 tasks with selected training trajectories. Fine-tuning Qwen3.6-35B-A3B on these trajectories improves performance over the base model by up to 11.5 points on user-related tasks and by an average of 4 points on general
benchmarks. Training on more user behavior data further improves user-related performance, and reinforcement learning after fine-tuning outperforms reinforcement learning from the base model by up to 7.7 points. These gains suggest that real-world user behavior is a scalable source of supervision for both user-centered capabilities and the broader intelligence of LLMs.
Read the full abstract ▾
All authors Yang Xiao, Yusong Sun, Haoyi Wu, Wenyang Hui, Weiqiang Hang, Luqing Wang, Zejian Wang, Zirui Tu, Jingsheng Mao, Shaobo Hu, Yang Luo, Jiale Guo, Jin Zhang, Yudan Liu, Zhaokai Luo, Ren Huan, Yao Hu, Chengyue Jiang, Wenjie Li, Chuan Mu
High Energy Physics (Phenomenology)
Mixed leptogenesis sources and low-energy neutrino portals
Yingnan Xu
A mixed leptogenesis source and its low-energy
neutrino portal depend on the same heavy-particle amplitudes. We determine how this common origin restricts matching cancellations and the scalar population produced during reheating. For two Majorana mass levels, each containing a degenerate pair, the inclusive
lepton-number-violating invariant fixes an allowed norm domain for the mixed dimension-five coefficient at specified threshold strengths. An aligned flavour texture makes the conventional source vanish as a
matrix and gives equal coupling norms for the two massive
neutrinos. A continuous family preserves the
neutrino-mass fit while relating the source to unequal light coupling strengths. The matched couplings give
benchmark vacuum lifetimes of $1.62\times10^{12}\,\mathrm{s}$ and $2.80\times10^{11}\,\mathrm{s}$, while reheating normalized to the
baryon abundance determines the primary spectrum. In the massless Born approximation with dilute outgoing states, bath-produced scalars carry $4.81\times10^{-5}$ of the primary scalar energy but contribute $11.1$ times its variance. The positive production functional converts the matching constraint into a conditional variance bound. We derive the scalar-mass dependence of stimulated emission and the Hartree moment equation, keeping the scalar mass and quartic as renormalized matching inputs. These results link the leptogenesis source to light-
neutrino decay and the finite-density quantities entering subsequent coupled transport.
Read the full abstract ▾
Artificial Intelligence
How to Build a Benchmark That Actually Measures Taste
Xiaofan Wu, Xi Zeng, Miaoxia Chen et al. (+8 more)
Expert-aligned "taste"
benchmarks should reward craft judgment, not the ability to game the test. We introduce TasteBench, a pairwise good-vs-bad
benchmark across visual, brand, book, and tech items under a frozen rubric with expert-only gold (panel n>=3; percent agreement >=0.60 primary gate; weak engagement labels train/analysis-only), together with a control protocol that separates craft judgment from test-gaming. Applying the protocol to a Round-1 pilot (primary_human_expert; three biological human experts; n=250 pairs) surfaces and quantifies three validity threats: two construction artifacts that inflate the trivial-baseline layer, and a difficulty ceiling that inflates every score. (1) Position: the preferred item is slot A with probability 0.956, so an always_item_a policy scores 0.956 (fair chance 0.5). (2) Lexical leakage: a filename
token cue scores 0.912. (3) Difficulty ceiling: craft domains show near-ceiling human agreement (book/brand/tech 1.0), and even under A/B randomization (eval_assignment_seed7; gold_side_A ~0.47) all five VLM cards reach 1.0 on craft, with only visual separating (~0.84-0.91; a post-hoc hard subset, n=107, leaves craft at 1.0). The protocol (expert-only gold, a weak-label firewall, side randomization at construction, filename scrubbing, and hard filters) makes each artifact measurable and, for the two construction artifacts, correctable; we release a reference eval harness and a side-randomization tool, and show the tool removes the position skew (0.916 to 0.495/0.505). The result is a calibrated view of what the
benchmark does and does not yet measure: position and leakage are fixable, whereas the craft-domain ceiling is a pair-difficulty limit that Round-2 must address. We do not evaluate engagement, era/circle conditioning, or calibration here, and we claim no general taste SOTA.
Read the full abstract ▾
All authors Xiaofan Wu, Xi Zeng, Miaoxia Chen, Peishan Chen, Shuyan Li, Chen Wang, Xiaohan Wang, Wanling Xu, Jiyun Yao, Hanyong Zhong, Jiahao Zhu
Materials Science
Finite-temperature adiabatic-connection reduced density-matrix functional theory: a unified framework for i-DMFT and TAO-DFT
Jingang Han, Huanjing Gong, Kai Luo et al. (+2 more)
Accurately describing chemical bond breaking requires capturing strong/static electron correlation, a major challenge for single-reference self-consistent-field methods such as Hartree–Fock and Kohn–Sham density-functional theory (DFT). Fractional occupations substantially improve this situation, as demonstrated by information-density-
matrix-functional theory (i-DMFT) and thermally-assisted-occupation DFT (TAO-DFT). Although useful, they are formulated within rather different theoretical frameworks, are somewhat semi-empirical, and their relationship remains unclear. Here we introduce finite-temperature adiabatic-connection reduced density-
matrix functional theory (FT-AC-RDMFT), in which i-DMFT and TAO-DFT emerge as different reductions of a unified framework. The effective
eigenvalue equation for natural orbitals and the
Fermi–Dirac occupation numbers follow directly from the variational principle, while a thermal adiabatic connection relates the empirical
entropy coefficient of i-DMFT to a characteristic temperature of the auxiliary non-interacting system. Within this framework, i-DMFT is the exact-exchange-based reduction, whereas TAO-DFT results when exact exchange is replaced by a density-based exchange-correlation functional. Numerical calculations confirm that i-DMFT, apart from a constant, coincides with the exact-exchange realization of the framework, and show that the improved dissociation behavior from finite-temperature occupations extends beyond exact exchange to hybrid and semilocal density functionals. For strongly correlated V2O3, finite-temperature occupations substantially reduce the severely overestimated non-
magnetic LDA bulk modulus, bringing it close to experiment. These results establish FT-AC-RDMFT as a common theoretical foundation for finite-temperature occupation-based electronic-structure methods in molecular and solid-state systems.
Read the full abstract ▾
All authors Jingang Han, Huanjing Gong, Kai Luo, Hongming Weng, Xinguo Ren
Computation and Language
Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine
Rui Hua, Yu Wei, Ziri Jin et al. (+15 more)
Large
language models have advanced medical
reasoning, but clinically grounded
reasoning in traditional Chinese medicine (TCM) remains challenging because prescription decisions require integrating domain knowledge, syndrome differentiation, treatment principles, herbal prescription composition, and dosage determination. We develop a TCM
language model family comprising models with 4 billion, 8 billion, and 14 billion parameters. The artificial intelligence contribution is a staged clinical
alignment framework integrating large scale continued pretraining on TCM and clinical records, complementary
reasoning supervision, and prescription-centered reinforcement learning (RL). We further formulate herbal prescription generation as a structured RL problem with prescription-level feedback, enabling direct optimization of clinical decision outputs beyond knowledge reproduction and generic instruction following. The engineering application is TCM clinical decision support, particularly herbal prescription recommendation. We evaluate the models on a public
benchmark containing 25,620 expert-verified items across 13 TCM knowledge and clinical
reasoning tasks and on a private retrospective
dataset of 4,348 spleen and stomach disease prescription cases. The 14 billion parameter reinforcement aligned model achieves a prescription generation F1 of 37.0 on the public
benchmark, compared with 32.3 for DeepSeek-R1 with 671 billion total parameters, and a herb-level F1 of 52.8 on the clinical
dataset with improved dosage agreement. Reinforcement post-training consistently improves prescription recommendation across all scales, while physician-source analysis shows that expert heterogeneity affects reward stability. These findings demonstrate a scalable pathway from domain grounding and
reasoning supervision to clinically oriented prescription decision support.
Read the full abstract ▾
All authors Rui Hua, Yu Wei, Ziri Jin, Zhuo Sun, Kai Chang, Jianan Xia, Zixin Shu, Xiaodong Li, Dongmei Jia, Fei Dong, Runshun Zhang, Jian Yu, Hao Xu, Haibin Yu, Jiansheng Li, Baoyan Liu, Wenjia Wang, Xuezhong Zhou
Robotics
PRISM: Precision Forcing for Generalist Vision-Language-Action Policies
Chenghao Yue, Peiyan Li, Hao Wang et al. (+5 more)
Coupling a pretrained
vision-
language model (VLM) with a
diffusion or flow-matching action expert has become the mainstream
vision-
language-action (VLA) paradigm for
embodied policies, yet they remain unreliable once a task demands precise manipulation, e.g., submillimeter cable insertion. We attribute this weakness to a training objective that averages flow-matching errors across contexts and flow times, allocating little supervision to the few decisive moments determining task success. Along the generative path, inference integrates a locally supervised velocity field, so equally penalized errors at different flow times can affect the executed action unequally. Consequently, precision-task performance deteriorates as physical tolerance tightens by orders of magnitude. We call this supervision imbalance across contexts and flow times Flow-Time Starvation. The remedy is to jointly align supervision allocation and representation learning with context-dependent precision demand, enabling the policy to recognize when greater precision is needed. We instantiate this precision-forcing strategy as Precision-aware Reweighting and Internalization for Skilled Manipulation (PRISM), which scores precision demand offline, strengthens flow supervision where errors are consequential and action signals are visible, and internalizes that demand in the VLM condition representation. Simulation and real-
robot experiments show that PRISM preserves or improves general-task performance while raising mean end-to-end success from 38.3% to 86.7% across drive connector insertion, bimanual connector mating, and screw tightening, substantially extending the precision boundary of existing
embodied policies without new sensors or observation modalities.
Read the full abstract ▾
All authors Chenghao Yue, Peiyan Li, Hao Wang, Lei Lv, Jiahao Chen, Huaping Liu, Yu Luo, Yuanlong Zhang
Machine Learning
Linear-Time Non-Local Codec Placement for Machine Learning Model Compression
Matteo Spallanzani
On-device inference imposes constraints on model storage and operand traffic and thus benefits from compressed operand representations, which mandate the use of encoding and decoding operators. However, naïve placement of codec operators can cancel the operand traffic gains sought from compression. In this work, I present an
algorithm to place codec operators into a source computational graph to make it compatible with target hardware. The edges of the graph are colored so that each induced subgraph is weakly connected and has a maximal node that both postdominates all subgraph inputs and dominates all subgraph outputs; this unique node - dubbed the $\textit{absolute dominator}$ - is the natural location to observe the traffic flowing through the subgraph and learn parametric codec operators. The
algorithm's time complexity is linear in the source graph's size. With respect to naïve local codec placement, the
algorithm reduces modeled operand traffic by $24\%$-$44\%$ across four models, including $24\%$ on SigLIP and $34\%$ on SmolLM2.
Read the full abstract ▾
Robotics
BGC-Nav: Cross-Altitude Multi-UAV Collaborative Navigation via Belief-Guided Coupling
Jiuwu Hao, Yueyang Wu, Liguo Sun et al. (+3 more)
Despite recent advances in Aerial
Vision-and-
Language Navigation (VLN), single Unmanned Aerial Vehicle (
UAV) search-and-rescue in outdoor scenarios remains challenging due to partial observability, making cross-altitude collaboration a promising direction. However, existing collaborative
navigation methods rely on precise target localization and rigid goal-dispatching paradigms, ignoring high-altitude observation uncertainty and suppressing low-altitude exploration autonomy. To address these issues, we introduce BGC-Nav, a training-free cross-altitude collaboration framework that enables robust
navigation via Belief-Guided Coupling (BGC). Specifically, the high-altitude
UAV maintains a Global Belief
Memory encoding task-conditioned priors, which the low-altitude
agent incorporates into decision-making via Local Exhaustion
Memory (LEM), Local Attraction Augmentation (LAA), and Directional Belief Prior (DBP) as an advisory bias rather than a rigid command. Extensive experiments on ESARBench show that BGC-Nav consistently outperforms state-of-the-art single-
agent and collaborative methods. Code is available at https://github.com/uestchjw/BGC-Nav.
Read the full abstract ▾
All authors Jiuwu Hao, Yueyang Wu, Liguo Sun, Haolin Song, Zao Zhang, Pin Lv
Cryptography and Security
Towards Merging-conditional Backdoor Unalignment against Large Language Models
Yukun Chen, Yidou Chen, Yiming Li et al. (+4 more)
Model merging has become widely adopted for enhancing the task-specific performance of Large
Language Models (LLMs) without additional training. While the specialized model from third-party platforms may undergo safety audits (e.g.,
backdoor detection), we reveal a novel and critical threat: One-sided Merging-Conditional
Backdoor (OMCB). OMCB remains dormant and undetectable within one standalone model but activates upon merging, triggering safety unalignment. We first theoretically analyze the existence and
geometric location of OMCB, revealing that the parameter shift crossing safety decision boundaries is the main cause of
backdoor activation. Building upon this insight, we propose SMOKE, a meta-learning-based attack framework. SMOKE implants OMCB via a bi-level optimization strategy: the inner loop synthesizes surrogate meta-vectors through random low-rank initialization and finite-step maximization, while the outer loop optimizes the target model by simulating the merging process. Furthermore, preliminary analysis shows that the injected OMCB has bounded generalization loss under unknown merging configurations. Extensive experiments across diverse model architectures and merging techniques validate the effectiveness of SMOKE and its resistance to existing
backdoor detections, highlighting a significant yet previously overlooked vulnerability in the model merging paradigm.
Read the full abstract ▾
All authors Yukun Chen, Yidou Chen, Yiming Li, Xinyu Zhang, Baosong Yang, Hongwei Yao, Zhan Qin
Artificial Intelligence
DSABench: Benchmarking Source Discovery, Coordination, and Execution for Multi-Database Agents
Jinlong Luo, Haoran Wu and Bo Xu
Most text-to-SQL
benchmarks provide the target database. In a large data catalog, however, choosing the sources is part of the problem: an
agent must find every database needed for a request, determine how their results fit together, and execute the resulting workflow. We present DSABench to evaluate these capabilities jointly. Its 815 human-reviewed tasks draw on Spider, BIRD, and LiveSQLBench; 618 require several databases to contribute, and 105 allow more than one interpretation of the required sources. Executable contracts define source participation, cross-source dependencies, and source-local execution, while RouteEnv lets
agents inspect public catalog evidence without revealing the gold annotations. In our routing-only study across seven model backends, the highest RA-Set score is 60.55%, compared with a highest RA-Graph score of 34.66% when coordination requirements are included. The gap becomes more pronounced when execution is required. Across four backends, median non-privileged Route+Exec-Graph success ranges from 6.69% to 7.98% without clarification and from 11.44% to 13.25% with one clarification; the best observed clarified configuration reaches 16.99%. On ambiguous tasks, clarification improves exact branch-source recovery by 39.8-43.2 percentage points. These findings illustrate why retrieving plausible databases or producing correct local SQL is not enough: an
agent must carry the right information through the entire multi-database workflow.
Read the full abstract ▾
Artificial Intelligence
Joint Discrete and SE(3) Diffusion for Protein Interface Design
Zhenqiao Song, Jianwen Xie and Lei Li
The design of high-affinity, target-specific
protein binders is central to the development of modern therapeutics. However, existing
protein-generation methods remain limited in this setting, as many generated designs fail to simultaneously achieve
geometric and physicochemical complementarity at binding interfaces. To address this challenge, we introduce PIDiff, a physicochemically enhanced
multimodal diffusion framework for
protein-
protein complex design. PIDiff jointly designs target-conditioned
protein sequences and structures by coupling
diffusion in discrete sequence space with
diffusion on the continuous (SE(3)) structural
manifold. At its core, PIDiff employs PIFormer, a novel architecture that interleaves geometry-aware invariant point
attention with global sequence self-
attention. We further curate PIBench, a
protein-
protein complex
dataset with diverse target scaffolds derived from the
Protein Data Bank (PDB). We first pretrain PIDiff on PIBench and subsequently fine-tune it for two therapeutically relevant applications: minibinder design and antibody design. PPFrame consistently outperforms baseline methods across sequence design success rate, structure binding energy, and sequence-structure co-designability on all tasks.
Read the full abstract ▾
Computer Vision
PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training
Yaolong Zhu, Peng Li, Jiahao Lu et al. (+8 more)
Feed-forward 3D reconstruction models have achieved remarkable progress through large-scale training and strong learned priors. However, they remain fragile when applied to dynamic in-the-wild
videos, where non-rigid motion, occlusions, and illumination changes are prevalent. A key limitation lies in their reliance on expensive depth and camera pose annotations, which hinders scaling to diverse real-world dynamic data and restricts generalization. To address this issue, we propose PURE, an unlabeled post-training refinement framework that improves depth and camera estimation without requiring ground-truth supervision. Instead of relying on annotations, PURE elegantly distills robust structural knowledge from state-of-the-art 2D priors into 4D feed-forward architectures. PURE leverages relative depth constraints, affine-invariant geometry
distillation, and pose refinement based on feature correspondences to stabilize
geometric predictions under challenging dynamic conditions. Extensive experiments on both synthetic and real-world dynamic
benchmarks demonstrate that PURE delivers consistent improvements across multiple state-of-the-art architectures. Furthermore, our data-efficient paradigm effectively mitigates domain shifts, successfully unlocking the architectural limits of these base models in challenging, in-the-wild dynamic scenes.
Read the full abstract ▾
All authors Yaolong Zhu, Peng Li, Jiahao Lu, Chengfeng Zhao, Mengfei Li, Chao Wang, Wenyue Chen, Zekai Gu, Chengwei Ren, Ronggang Wang, Yuan Liu
Sound
AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation
Yixuan Li, Xuenan Xu, Zeyu Xie et al. (+1 more)
Speech-conditioned generation maps
speech signals to target audio outputs. Prior end-to-end
speech-conditioned generative models achieve high fidelity in clean acoustic conditions, but their performance degrades substantially under environmental noise. While prior noise-robust approaches have achieved significant success in feature-level purification, maintaining consistent generation under clean and noisy conditioning remains a key challenge. To address this, we propose AlignAudio, a noise-robust generative framework based on dual
alignment: (i) aligning the representations of clean and noisy
speech to preserve semantic cues, and (ii) enforcing generation-level consistency within a flow matching paradigm to improve conditioning fidelity. Experiments on
speech-to-audio (STA) and voice conversion (VC) tasks demonstrate that AlignAudio maintains performance comparable to baselines on clean
speech while significantly outperforming them across various noisy conditions. Furthermore, the proposed dual-
alignment strategy is applicable to both single- and multi-stream
speech conditioning and can be integrated into different flow matching-based generation frameworks and post-training settings. Audio demonstrations and qualitative comparisons: \href{https://alignaudio.github.io/AlignAudio}{\textcolor{cyan}{https://alignaudio.github.io/AlignAudio}}.
Read the full abstract ▾
All authors Yixuan Li, Xuenan Xu, Zeyu Xie, Mengyue Wu
Machine Learning
Understanding Hidden Spatial Preferences in Bayesian Optimization
Maria Bånkestad and Jens Sjölund
Bayesian optimization uses posterior uncertainty to decide where to explore, but this uncertainty is not spatially neutral. On bounded domains, Gaussian-process posterior variance is typically larger near faces, edges, and corners, giving variance-based acquisition functions a systematic boundary bias. This spatial preference is usually inherited from the surrogate rather than chosen as part of the exploration strategy. We separate these roles by keeping the predictive model fixed and modifying the spatial preference of the exploration term. We control the preference with spatial weight fields and amortize their construction with neural surrogates. Controlled experiments show that the Gaussian process' default boundary bias changes which parts of the domain are explored and which optima are reached. We compare three alternative exploration principles and find, across standard
benchmark functions and
stochastic robot-pushing tasks, that they can often lower regret, particularly early in the optimization. The spatial structure of posterior uncertainty is therefore not a neutral default: it shapes the exploration strategy and can materially affect optimization performance.
Read the full abstract ▾
Statistical Methodology
The price of a weak shadow variable: inference under nonignorable missingness as relevance vanishes
Michael Bücker
When an outcome is missing not at random, identification is commonly restored by a shadow variable: a
covariate that predicts the outcome but is excluded from the response mechanism. The literature treats the first requirement, relevance, as a yes-or-no condition. We make it continuous, parametrizing it by a scalar that scales the shadow variable's entire contribution to the moment conditions, and ask what inference costs as that scalar vanishes. One functional of the inverse weight governs the answer. We characterize it exactly, show that it fixes the effective sample size, and use it to sharpen the rates of the
estimator that avoids the weight. The characterization is concrete. Whether the functional saturates or diverges turns not on boundedness of the outcome but on whether the tilting variable has an atom at its essential supremum: a binary outcome saturates, a uniform one does not. It also bounds how far a scanned set reaches, and that reach grows only as the square root of the logarithm of the sample size, so a thousandfold increase buys one unit of tilt while the set to be scanned widens. A reanalyzed credit-scoring study shows the cost: a characteristic an optimizing selector uses cannot satisfy exclusion.
Read the full abstract ▾
Sound
VoTSpeech: Decoupling Voice Design from Speech Generation in Instruction-Following TTS
Wenbing Yang, Qihang Lu, Zihan Sun et al. (+4 more)
Instruction-following text-to-
speech (TTS) typically leaves voice design implicit, as conventional speaker
embeddings encode reference audio rather than text-driven targets. We propose VoTSpeech, which decouples voice design from
speech generation via an explicit intermediate voice latent. Built on a shared
language model backbone, VoTSpeech first predicts a continuous voice latent from text instructions using a flow-based module. This latent serves as a shared condition for both the
language model and the Acoustic DiT, guiding autoregressive sequence modeling and acoustic latent generation, respectively, before an audio VAE decoder converts the acoustic latents into waveforms. To capture speaker identity and complementary acoustic nuances, the voice latent is jointly supervised by speaker
embeddings and temporally pooled audio VAE features. With task-specific adaptation, VoTSpeech performs strongly on InstructTTSEval-ZH, demonstrating competitive capabilities against strong open-source models while maintaining high naturalness. These results confirm that explicit voice latent design and its conditioning interface effectively empower text-driven voice design for controllable
speech synthesis. Code, model, and audio samples are available at https://github.com/ywbn/VoTSpeech .
Read the full abstract ▾
All authors Wenbing Yang, Qihang Lu, Zihan Sun, Peilei Jia, Yingming Gao, Ya Li, Jun Gao
Artificial Intelligence
AcrossVAM2.0: Conflict-Aware Point Supervision for Parameter-Efficient Video Diffusion Adaptation
Nan Wu and Yee Hung Hong
Explicit point correspondence is attractive for adapting
video generators: it describes how visible surfaces move, but can overwrite the appearance prior learned by a large pretrained model. We study this tension in a 5.01B-parameter text-to-
video diffusion transformer. ACROSSVAM2.0 combines a confidence-weighted track-and-visibility head, zero-initialized residual feedback, and asymmetric PCGrad that removes only the auxiliary component opposing the primary flow-matching gradient on shared LoRA parameters. The design preserves the generator exactly at initialization and protects its primary update during adaptation. In a four-way ablation trained for 1,000 steps with three independent seeds, the full method lowers KLT forward-backward cycle error in all three seeds relative to a matched flow-only continuation (mean seed-level difference -0.00711, SD 0.00505), while robust sharpness remains positive in all three. An expanded 24-
prompt evaluation (216
videos) yields 9.7% lower aggregate CoTracker3 cycle error than the matched control and near-matched performance on six VBench dimensions; however, the seed-level tracking effect is heterogeneous and I3D-FVD regresses from 0.1824 to 0.2022. These results support a bounded claim: conflict-aware adaptation improves correspondence consistency without broad perceptual degradation, but does not uniformly improve
video quality. We release equations, pseudocode, matched outputs, source tables, and artifact provenance.
Read the full abstract ▾
Rings and Algebras
Diagonalization of skew-Hermitian dual quaternion matrices and $\phi$-Hermitian dual quaternion matrices
Cailing Yao and Bingzhe Hou
In this article, we present the diagonalization of skew-Hermitian dual quaternion
matrices in the sense of
unitary equivalence. For a unit quaternion $\phi$, we also obtain the diagonalization result of $\phi$-Hermitian dual quaternion
matrices in the sense of
unitary $\phi$-congruence, which generalizes the Autonne–Takagi factorization of symmetric complex
matrices and $\phi$-Hermitian quaternion
matrices.
Read the full abstract ▾
Robotics
DexCast: Learning Real-World Dexterous Control from Human Videos
Zihan Gao, Yuhong Zhang, Mengzhe Wang et al. (+7 more)
Recent advances in 3D hand-object interaction (HOI) perception have opened new opportunities for learning dexterous robotic skills from human
videos. However, existing dexterous imitation learning methods often rely on costly and manually teleoperated
robot demonstrations, requiring substantial human effort. Therefore, we build DEXCAST, a framework that learns dexterous robotic hand control directly from
monocular RGB-D
videos by leveraging joint HOI reconstructions, without requiring any teleoperation. Furthermore, how to model high-dimensional robotic hand motion and extract temporal context to inform future action generation remains a key challenge. To this end, we propose a DexHand Motion Perception Module (DMPM) to capture inter-joint coordination and temporal dependencies in compact latent representations that condition our
diffusion policy. Extensive real-world experiments demonstrate that DEXCAST achieves exceptional performance across diverse dexterous manipulation tasks.
Read the full abstract ▾
All authors Zihan Gao, Yuhong Zhang, Mengzhe Wang, Kaisheng Liu, Shengpeng Li, Siyao Xiao, Runqing Cheng, Xiao Lin, Zhifang Liu, Haoqian Wang
Optics
Selective spatiotemporal mode-locking in multimode Mamyshev oscillators
Changfeng Wang, Jia Liu, Yutai Zhao et al. (+6 more)
Spatiotemporal mode-locking (STML) in multimode fibers introduces spatial degrees of freedom for ultrashort pulse generation, yet flexible manipulation of transverse mode compositions within multimode
solitons remains challenging. Here, we propose a spectrum-to-mode mapping strategy in multimode Mamyshev oscillators (MOs) to selectively synchronize specific transverse modes through synergistic cross-phase modulation and offset spectral filtering. Meanwhile, four-wave mixing acts to stabilize intermodal phase relationships, facilitating selective STML characterized by diverse mode compositions with matched group velocities. Spatiotemporal
solitons containing the pure LP01 mode, degenerate LP11 modes, or LP02+LP21 composite modes are selectively realized and mapped across the parameter space spanned by intracavity gain and filter detuning. Furthermore, intracavity collisions between coexisting mode groups with disparate group velocities are demonstrated to enable dynamic mode selection. Beyond the simulation of six modes in graded-index multimode fibers, selective STML is also demonstrated in MOs based on step-index multimode fibers and fibers supporting more transverse modes, confirming the generality of our approach. This strategy offers a versatile and robust pathway for transverse mode regulation and provides new insights into full dimensional structured light manipulation in multimode ultrafast fiber
lasers.
Read the full abstract ▾
All authors Changfeng Wang, Jia Liu, Yutai Zhao, Ran Xia, Wenjun Ni, Chunyong Yang, Xiahui Tang, Gang Xu, Perry Ping Shum
Group Theory
Sylow $2$-Subgroups of Finite Groups with a Single Conjugacy Class of Involutions
Tianze Li and Yu Zeng
We solve Brauer's Problem 33 by determining the finite $2$-groups that occur as Sylow $2$-subgroups of finite groups with a single conjugacy class of involutions. Besides the Sylow $2$-subgroups arising from the relevant non-abelian simple groups in Table 1, these are precisely the homocyclic, generalized quaternion, and Suzuki $2$-groups. The classification of finite simple groups is used in this paper.
Read the full abstract ▾
Machine Learning
Accelerating Cross-Model LLM Inference via Attention Map Reuse
Zhan Jin, Yuze Luo, Bin Cui et al. (+1 more)
LLM-augmented data workflows often involve multiple heterogeneous models operating over substantial shared context, such as schemas, tool specifications, interaction history, and intermediate results. Although prefix caching can reduce prefilling overhead, existing approaches are largely limited to reuse within the same model because KV states are tightly coupled to model-specific architectures. We present MapFlow, a system for efficient heterogeneous LLM serving via cross-model
attention map reuse. Instead of reusing KV states, MapFlow reuses
attention maps, which capture
token dependency patterns and are more transferable across models. To enable efficient and accurate reuse, we combine partial recomputation with lightweight linear translation across layers and heads. To make
attention reuse practical for long contexts, we further introduce block-level sparse compression and a fused
retrieval kernel. Experiments show that MapFlow reduces prefilling latency and improves end-to-end serving efficiency while preserving generation quality across heterogeneous model pairs and multi-turn routing workloads. These results suggest that
attention maps provide an effective reusable state for heterogeneous LLM serving, especially in prefix-heavy data workflows. Our code is available: https://github.com/PKU-DAIR/MapFlow.
Read the full abstract ▾
All authors Zhan Jin, Yuze Luo, Bin Cui, Xupeng Miao
Machine Learning
One-Way Coupling via Patchwise Adaptive Normalization in Transformer Surrogates
Emmanuel Gottlob, Hugo Thimonier, Ludovico Buizza et al. (+3 more)
Many physical systems exhibit one-way coupling: exogenous fields such as medium density or obstacle geometry influence the dynamics without being affected by them. We investigate how explicitly representing these fields can improve the accuracy and computational efficiency of
transformer-based PDE surrogates. Building on spatially adaptive normalization, we introduce Patchwise Adaptive Normalization (PAdaNorm), which partitions exogenous fields into patches aligned with the state tokenization. We evaluate PAdaNorm on
datasets from three different domains, using a Walrus-inspired
transformer architecture. Across the three PDE families, PAdaNorm is on par with or up to 16% better than parameter-matched baselines in mean long-horizon variance-scaled RMSE on 60-step autoregressive rollouts. We also find that PAdaNorm better maintains hard physical constraints over long rollouts, such as preventing flow into impenetrable solid regions in porous media. When the conditioning is static, PAdaNorm caches the conditioning
embeddings once and reuses them across the entire rollout, reducing inference FLOPs per step by up to 36% compared with parameter-matched baselines. An ablation over eight conditioning variants shows that modulating a single
attention axis (temporal or spatial) suffices and that a lightweight shared MLP across blocks remains competitive with per-block projections.
Read the full abstract ▾
All authors Emmanuel Gottlob, Hugo Thimonier, Ludovico Buizza, August Martens, Alexandre Gavaudan, Thiago Guzella
Distributed Computing
Vesta: Queueing-Aware LLM Scheduling for Real-World Workloads
Lancheng Zou, Bowen Li, Wei Mao et al. (+6 more)
Agentic applications generate multi-turn sequences of LLM requests, with each new turn extending the context accumulated from prior interactions and tool calls. Prefix caching reuses the KV cache of earlier turns and avoids redundant prefill, but routing every turn to its cache-affine instance can create severe local queues while capacity remains idle elsewhere. Remote KV cache access relaxes this tension, yet migrating execution adds transfer work and is harmful when the cluster is already congested. Thus, deciding where to execute a request requires
reasoning jointly about cache locality, queueing, and the current operating point of the cluster. We present Vesta, a queueing-aware scheduler for distributed agentic LLM serving. Vesta assigns each session a stable holder for its authoritative KV cache while independently selecting an executor for every request. Grounded in classical queueing theory, its objective accounts for backlog, reusable prefixes, KV cache transfer, and the queueing externality of additional service demand; it migrates execution to recover idle capacity when beneficial and favors placements that add the least prefill and transfer work as congestion rises. Vesta also migrates reusable prefixes across length buckets to avoid cold starts. On real-world agentic workloads, Vesta improves throughput by 14.0% and reduces mean TTFT by 57.8% over the state-of-the-art scheduler in a PD-colocated deployment. In PD-disaggregated deployments, it reduces mean TTFT by up to 18.1% and P99 TTFT by up to 29.0% at matched throughput.
Read the full abstract ▾
All authors Lancheng Zou, Bowen Li, Wei Mao, Wenbin Ye, Lecheng Li, Kai Liu, Chao Deng, Jianchen Zhu, Bei Yu
Computer Vision
Demiurge: Forging Navigable 4D Worlds via Autoregressive Video Rerendering
Hanxin Zhu, Jianqi Ma, Cong Wang et al. (+10 more)
Recent advances in
video diffusion enable novel-view
video synthesis from a single input
video, supporting world modeling,
embodied intelligence, and robotic simulation. However, existing methods process camera trajectories independently, lacking the cross-trajectory consistency needed for coherent, navigable 4D worlds. We introduce Demiurge, an autoregressive
video rerendering pipeline built on a dynamic 4D point-cloud
memory cache. It promotes cross-trajectory consistency through four components: (1) an appearance
video diffusion model that synthesizes photorealistic novel-view
videos conditioned on the 4D
memory; (2) a
memory-consistent
video depth completion model that aligns known-region depths with cached geometry and completes missing regions, mitigating scale ambiguity and discontinuities during
memory updates; (3)
memory-aware dual-stream warping that provides high-fidelity visual guidance and occlusion cues for novel-view synthesis; and (4) geometry-aware
video refinement that enhances perceptual quality. Extensive experiments demonstrate state-of-the-art performance and three key capabilities: coherent spatiotemporal
lattice construction over dense multi-view trajectories; large-parallax
video rerendering under challenging camera motions, including 180-degree rotations with no input-view overlap; and geometry-faithful outputs that can be directly optimized into high-quality 3D Gaussian Splatting representations with minimal artifacts. Project page: https://hanxinzhu-lab.github.io/demiurge_project_page/.
Read the full abstract ▾
All authors Hanxin Zhu, Jianqi Ma, Cong Wang, Zhihao Hu, Junyao Gao, Tianyu He, Junyan Lin, Jiayin Xiao, Jiateng Shou, Sen Liang, Weidong Zhang, Zhibo Chen, Jun Zhang