Searcharxiv⌕ Search

arXiv subjects

Zheng Li

Publications and source records attributed to Zheng Li.

At least 55 records · Page 3Linked to original sources
arXiv2026

Optimize Surgical Triplet Recognition: A Knowledge-Driven Mixture-of-Experts Solution

Surgical action triplet recognition constitutes a critical task in context-aware robot-assisted surgery, facilitating automatic surgical action perception by identifying instrument, verb, target, and their association. However, existing works struggle to analyze such complex surgical scenes due to three main issues: (1) component-level optimization conflicts caused by entangled feature spaces, (2) category-level optimization conflicts arising from severe data imbalance, and (3) lack of domain knowledge guidance that limits model interpretability and robustness. To address these challenges, we propose a Mixture-of-Experts-guided Co-Optimization (\textit{MoeCo}) framework powered by knowledge-driven learning. Within the co-optimization pipeline, to first mitigate component-level conflicts, we introduce a component-tailored adapter that disentangles task-specific features across spatial-temporal regimes, facilitating effective component specialization. Next, we develop a coordinated gradient learning strategy to handle category-level conflicts, which adaptively rebalances positive-negative gradients to enhance the perception of rare categories. Notably, inspired by surgical domain expertise, we introduce a knowledge-driven mixture-of-experts mechanism that dynamically integrates multimodal large language model-guided knowledge via activated experts, thereby enriching the co-optimization pipeline with more expressive and robust representations. Extensive experiments on the public CholecT45 and CholecT50 datasets confirm the effectiveness of the proposed co-optimization pipeline and the superiority of dynamic priors integration via the knowledge-driven mixture-of-experts mechanism.

cs.CV↗
arXiv2026

On the existence of the KMS spectral gap in Gaussian quantum Markov semigroups

In arXiv:2405.04947, it was shown that a Gaussian quantum Markov semigroup on the $d$-mode bosonic Fock space with a unique faithful normal invariant state has a positive GNS spectral gap if and only if the matrix $[U \overline{V}]$, formed from the coefficients of the Kraus operators, has $2d$ linearly independent columns. In this paper, we establish the corresponding criterion for the KMS spectral gap. After standardizing the invariant Gaussian state and grouping the modes according to their inverse temperatures, let $U_n$ and $V_n$ denote the submatrices of $U$ and $V$, respectively, corresponding to the $n$-th equal-temperature block. We prove that $\ker U_n=\ker V_n$ for every $n$, and that the KMS spectral gap is positive if and only if this common kernel is trivial for every equal-temperature block. Thus, whereas the GNS spectral gap requires a global maximal-rank condition on the Kraus coefficients, the KMS spectral gap requires maximal column rank only within each equal-temperature block.

math.FA↗
arXiv2026

Tac4Loco: Learning Spatiotemporal Plantar Pressure Representations for Humanoid Locomotion

Humanoid robots are expected to traverse complex terrains, where the plantar support may vary dramatically due to foot placement errors, ground properties, and transient dynamics. To achieve robust locomotion, the robots are required to adapt to uneven terrain and uncertain foot--ground interactions. Existing locomotion policies rely primarily on proprioception or exteroceptive terrain perception, where the former provides only indirect evidence of plantar support, while the latter predicts contact conditions before touchdown but cannot observe the actual support in real-time. Although some studies incorporate plantar contacts as an auxiliary perception, they rely mainly on summary statistics, overlooking the spatial topology of plantar pressure, which provides a more direct characterization of the realized contact state. To bridge this gap, we present Tac4Loco, a tactile-perceptive framework that incorporates multi-array plantar pressure as direct feedback for humanoid locomotion. We formulate a topology-preserving ordinal representation to map simulated and physical sensor signals into a shared observation space, with a dual-branch encoder for extracting their spatial and temporal representations. Subsequently, the learned spatiotemporal features are integrated with augmented proprioception including terrain estimation cues, and provided to an asymmetric actor-critic architecture for policy learning. Extensive simulation and real-world experiments demonstrate improved tracking performance and support adaptation on terrains with inclined, partial, asymmetric, and changing support. We further demonstrate its zero-shot deployment on unseen compliant and unstructured terrains, including a foam platform and a gravel road. All code and experimental configurations will be released as open-source to facilitate reproducibility.

cs.RO↗
arXiv2026

Boundary-Aligned Contribution Routing for Robust Optical--SAR Object Detection

Optical imagery provides rich appearance cues, whereas synthetic aperture radar (SAR) offers observations that are less sensitive to illumination and weather, making optical--SAR fusion attractive for remote-sensing object detection. However, the presence of multiple modalities does not guarantee beneficial fusion: imperfect spatial, temporal, and semantic correspondence can make an otherwise intact stream conditionally harmful and induce negative cross-modal transfer. We handle this issue through a model-specific task-utility perspective and learn task-conditioned contribution routing using detection supervision alone. The proposed fusion-boundary-aligned routing regulates each modality's contribution before the first learned cross-modal feature-value mixing operation. For architectures with frequent shallow interaction, a Feature Router performs cross-conditioned, group-addressable modulation near the input; for dual-backbone architectures, a Dual-Statistic Semantic Router predicts stream-level contribution weights from modality-specific average and maximum statistics before late semantic fusion. The routers require no explicit utility supervision, quality labels, reconstruction, or distillation. Experiments on M4-SAR and SpaceNet6-OTD cover nominal full inputs, controlled correspondence shifts, missing modalities, and four nonzero modality-corruption scenarios. Across the reported clean-training controls, routing improves full-input $\text{mAP}_{50}$ by 0.5--5.9 points. Relative to the corresponding modality-dropout baselines, it raises missing-modality $\text{mAP}_{50}$ by 7.6--41.6 points and reduces the negative-transfer rate by up to 12.7 percentage points. Spearman correlations between the learned routing weights and model-specific leave-one-modality-out utility range from 0.45 to 0.66, supporting the task-utility interpretation of the routing coefficients.

cs.CV↗
arXiv2026

Spectral Analysis for Gaussian Quantum Markov Semigroups

Let $(T_t)_{t\geq 0}$ be a Gaussian quantum Markov semigroup with a faithful normal invariant state $ρ$. For every $s\in[0,1]$, the $s$-embedding associated with $ρ$ induces a contraction semigroup $(T_t^{(s)})_{t\geq 0}$ on the Hilbert--Schmidt space $\mathcal B_2(\mathsf h)$; let $L^{(s)}$ denote its generator. Without assuming symmetry or quantum detailed balance, we determine the full spectra of $L^{(s)}$ and $L^{(s)\ast}$: they consist, respectively, of the non-negative integer combinations of the eigenvalues of the phase-space drift matrix and of their complex conjugates. We also diagonalize the self-adjoint closure of $L^{(s)\ast}+L^{(s)}$ and obtain an explicit formula for the spectral gap. Using quantum characteristic functions, we represent $T_t^{(s)}$, up to unitary equivalence, as a complex Gaussian integral operator and prove that its kernel is square-integrable for every $t>0$. Hence $T_t^{(s)}$ is a Hilbert--Schmidt operator on $\mathcal B_2(\mathsf h)$ for every $t>0$, and every induced semigroup is immediately compact. Consequently, $L^{(s)}$ and $L^{(s)\ast}$ have compact resolvent for all $s\in[0,1]$, and their point spectra exhaust their full spectra. These results provide a full quantum counterpart of classical Ornstein--Uhlenbeck spectral theory.

math.FA↗
arXiv2026

Modular TTT: Rethinking Test-Time Training as Composable Modules

Test-time training (TTT) views sequence modeling as an online learning problem in which fast weights are updated by an internal learning rule. Despite the growing number of TTT variants, existing approaches typically hard-code each variant separately, which makes it difficult to design new TTT methods and to isolate the role of each component. To address this, we propose Modular TTT, a framework that represents the inner learner as a directed acyclic graph and exposes the fast-weight network, loss function, learning rate, weight decay, and normalization as explicit design dimensions. Modular TTT automatically composes primitive-level train-view forward, train-view backward, and causal query-view rules into the full graph-level TTT computation, including the fast-weight state transition. Using Modular TTT, we systematically ablate the components of TTT and find that small learning-rate initialization, weight decay, and a single-layer nonlinearity improve performance, while MSE and inner-product losses perform similarly. Deeper fast-weight networks and normalization tend to hurt performance because they induce excessively large activations, while residual connections and gating provide little measurable benefit. Guided by these findings, we train the best resulting variant as 410M- and 1.45B-parameter models on 100B tokens, and observe training loss and benchmark performance comparable to Gated DeltaNet.

cs.LG↗
arXiv2026

GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning

Embodied AI research is undergoing a shift toward vision-centric perceptual paradigms. While massively parallel simulators have catalyzed breakthroughs in proprioception-based locomotion, their potential remains largely untapped for vision-informed tasks due to the prohibitive computational overhead of large-scale photorealistic rendering. Furthermore, the creation of simulation-ready 3D assets heavily relies on labor-intensive manual modeling, while the significant sim-to-real physical gap hinders the transfer of contact-rich manipulation policies. To address these bottlenecks, we propose GS-Playground, a multi-modal simulation framework designed to accelerate end-to-end perceptual learning. We develop a novel high-performance parallel physics engine, specifically designed to integrate with a batch 3D Gaussian Splatting (3DGS) rendering pipeline to ensure high-fidelity synchronization. Our system achieves a breakthrough throughput of 10^4 FPS at 640x480 resolution, significantly lowering the barrier for large-scale visual RL. Additionally, we introduce an automated Real2Sim workflow that reconstructs photorealistic, physically consistent, and memory-efficient environments, streamlining the generation of complex simulation-ready scenes. Extensive experiments on locomotion, navigation, and manipulation demonstrate that GS-Playground effectively bridges the perceptual and physical gaps across diverse embodied tasks. Project homepage: https://gsplayground.github.io.

cs.RO↗
arXiv2026

AROpt: An Optimization Method for Autoregressive Time Series Forecasting

Current time-series forecasting models are primarily based on transformer-style neural networks. These models achieve long-term forecasting mainly by scaling up the model size rather than through genuinely autoregressive (AR) rollout. From the perspective of large language model training, traditional time-series forecasting model training ignores the monotonic error-growth heuristic. In this paper, we propose a novel training method for time-series forecasting that enforces two key properties: (1) AR prediction errors should increase with the forecasting horizon. Violations of this trend are interpreted as rollout inconsistency and are softly penalized during training, and (2) the method enables models to be able to concatenate short-term AR predictions to form flexible long-term forecasts. Empirical results demonstrate that our method establishes a new state-of-the-art across multiple benchmarks, achieving an MSE reduction of more than $10\%$ compared to iTransformer and other recent strong baselines. Furthermore, it enables short-horizon forecasting models to perform reliable long-term predictions at horizons over 7.5 times longer. Code is available at https://github.com/LizhengMathAi/AROpt

cs.LG↗
arXiv2026

Logarithmic Aging Diffusion from a Multiplicative Event Clock: Rare Event Statistics, Ultraslow Transport, and Ensemble-Time Inequivalence

Logarithmic time dependences occur in many aging materials, but neither a $\ln t$ relaxation law nor a $1/t$ event rate uniquely identifies the underlying stochastic mechanism. We examine a specific log-aging process defined by iterating the age-conditioned forward-recurrence law after every event. This rule makes the event times multiplicative: the logarithmic ratios $U_n=\ln(T_{n+1}/T_n)$ are independent and identically distributed with an explicit non-exponential density. Consequently, both the mean and the variance of the event count grow linearly with $\ln(t/t_0)$, while the density of the $n$th event time has a log-normal central sector and a fixed-$n$ algebraic far tail. These clock statistics generate logarithmic drift and spreading, an Einstein relation under local detailed balance, and ultraslow transit and target-survival laws. They also separate trajectory reproducibility from ensemble--time equivalence: the relative scatter of the time-averaged mean-square displacement decays as $1/\ln(T/t_0)$, although its mean does not converge to the ensemble lag MSD. We distinguish the exact event-level construction from its diffusion-limit generalized Fokker--Planck and random-clock subordination representations, and from a generalized-Langevin closure that can match selected responses and covariances but need not reproduce event counts or rare-duration statistics. The proposed clock is therefore tested not by a single logarithmic curve, but by the joint, no-refitting consistency of multiplier, count, transport, first-passage, and finite-window observables.

cond-mat.stat-mech↗
arXiv2026

Irreducibility of the tensor product of Yangian \( \mathrm{Y}(\mathfrak{gl}_{m|n}) \) evaluation modules

The evaluation homomorphism from the super Yangian \( \mathrm{Y}(\mathfrak{gl}_{m|n}) \) to \( \mathrm{U}(\mathfrak{gl}_{m|n}) \) induces a \( \mathrm{Y}(\mathfrak{gl}_{m|n}) \)-module structure on any finite dimensional simple \( \mathrm{U}(\mathfrak{gl}_{m|n}) \)-module \( L(λ) \). In this paper, we give necessary and sufficient conditions for the tensor product of such evaluation \( \mathrm{Y}(\mathfrak{gl}_{m|n}) \)-modules, \( L_g(λ) \otimes L_h(γ) \), to be simple, provided each of \( λ\) and \( γ\) is either covariant tensor or essentially typical. Our proof is based on the existence of a Gelfand--Tsetlin basis for finite dimensional simple \( \mathrm{U}(\mathfrak{gl}_{m|n}) \)-modules with highest weights that belong to these two families: covariant tensor and essentially typical. The obtained result is a super analogue of the Molev's result for the classical Yangian \( \mathrm{Y}(\mathfrak{gl}_n) \). Combining this with the binary property of tensor products of covariant evaluation modules, we obtain an irreducibility criterion for arbitrary tensor products of covariant evaluation modules.

math.RT↗
arXiv2026

Isolated but Exposed: Persistence-Based Memory Extraction Attack on LLM Agents

LLM-based agents extend large language models with long-term memory (LTM) that persists privacy-sensitive user data across sessions. Production systems mitigate extraction risks through memory isolation, binding each user's LTM to a unique identifier. This defense has blocked known attacks on shared storage, fostering the assumption that isolated LTM is secure. We identify the tool interface as an overlooked attack surface. Agents routinely embed LTM-retrieved data in tool invocation parameters, enabling a malicious tool to exfiltrate private memory without violating user-level isolation. Naive adaptations of user-side extraction techniques fail because the adversarial command's semantics interfere with retrieval precision, and platform-imposed tool-call limits constrain the extraction budget per trigger. We present SPORE, the first extraction attack designed for this threat model. SPORE decouples the adversarial command from retrieval anchors by persisting the command in short-term memory and emitting semantically pure anchors in tool responses. The restored retrieval precision enables a geometric coverage optimization over the embedding space that systematically steers anchors toward unexplored memory regions. To sustain extraction beyond tool-call limits, SPORE persists reactivation payloads in memory that automatically resume the attack within and across sessions without additional user triggers. SPORE achieves an 80.0% record extraction rate with unlimited triggers and 47.0% with only 20 triggers. In multi-user deployments, attackers can link extracted records to user identities, enabling targeted surveillance. These results demonstrate that memory isolation alone is insufficient and call for reexamining tool-side trust boundaries in agent architectures.

cs.CR↗
arXiv2026

Local Causal Structure Learning in the Presence of Latent Variables and Selection Bias

Discovering the direct causes and effects of a target variable from observational data is a fundamental problem in causal discovery, with broad applications in domains such as gene regulatory analysis and biomedical research. Existing causal discovery methods either learn a global causal structure, which incurs substantial computational cost, or assume the absence of latent variables and selection bias, assumptions that are often violated in real-world settings. Motivated by these challenges, we study local causal structure learning in the presence of latent variables and selection bias. Specifically, we first characterize a local region that enables target-specific causal discovery without recovering the entire global structure. We then establish a theoretical bridge between causal information learned from the observed distribution induced on this local region and the corresponding information in the global causal structure. Building on these foundations, we propose LoCaLS, a local causal structure learning algorithm that is sound and complete under standard assumptions and identifies the same direct causes and effects of a target variable as those identifiable by global causal discovery methods, while allowing for latent variables and selection bias. Extensive experiments on random and real-world structures demonstrate that the proposed method consistently achieves higher structural accuracy than existing local methods while requiring substantially less computational effort than state-of-the-art global methods. Furthermore, applications to two real-world gene expression datasets reveal biologically plausible target-specific causal structures, demonstrating its practical applicability in large-scale biological data analysis.

cs.LG↗
arXiv2026

QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides

Rollout generation is a major bottleneck in Reinforcement Learning (RL) for Mixture-of-Experts (MoE) Large Language Models, motivating low-precision rollout acceleration such as FP8. As an emerging low-precision format, NVFP4 combines fine-grained scaling for accuracy preservation with native W4A4 FP4 GEMMs for higher throughput than FP8. However, we find that directly applying NVFP4 to MoE RL rollout is impractical. NVFP4 rollout with BF16 training collapses after roughly 150 steps, accompanied by rapidly growing rollout-trainer log-probability gaps. Through training-inference error analysis and controlled ablations, we identify activation error, rather than weight error, as the dominant source of FP4 RL instability: weights can be synchronized and aligned by a shared quantization-dequantization path, whereas activations are recomputed online and error is amplified by the coarse E2M1 grid. Therefore, to stabilize NVFP4 RL for MoE, we propose QUantization-error Alignment across Dual Sides (QUADS). On the trainer side, we introduce Asymmetric Quantization-Aware Training fake-quantizing weights while keeping activations unquantized for better alignment. On the rollout side, Residual Activation Compensation corrects high-error activation channels while preserving native W4A4 GEMMs. In our MoE RL experiments on several benchmarks, QUADS achieves BF16-level accuracy, improves average pass@1 by 21.49 points over naive NVFP4 RL, and delivers ~16% higher rollout throughput than FP8.

cs.LG↗
arXiv2026

Central Elements and Determinantal Identities in the Elliptic Quantum Algebra \( \mathcal{A}_{q,p}(\widehat{\mathfrak{gl}}_N)\)

Elliptic quantum algebra is the algebraic structure characterized by the elliptic solution of the Yang-Baxter equation. In this paper, we construct a family of central elements \( \mathfrak{z}(z) \) for the elliptic quantum algebra \(\mathcal{A}_{q,p}(\widehat{\mathfrak{gl}}_{N})\) and show that they can be expressed as quantum determinants, yielding an elliptic analogue of the Liouville formula. In addition, we establish determinantal identities, including Jacobi's ratio theorem and Sylvester's theorem.

math.QA↗
arXiv2026

Event Stream based Multi-Modal Video Anomaly Detection: A Benchmark Dataset and Algorithms

Video anomaly detection (VAD) is critical for automated surveillance but remains fragile under challenging conditions such as illumination variations, fast motion, and complex backgrounds when relying solely on visible light videos. To address these limitations, we propose EVAD, an event enhanced VAD framework that jointly exploits conventional video and event streams captured by bio inspired event cameras. Event sensors asynchronously capture brightness changes with high temporal resolution, offering robustness to motion blur and extreme lighting, and providing motion salient cues complementary to video based visual information. To support multi modal VAD research, we construct a large scale visible event benchmark comprising 6.3 billion events and 376,368 video frames collected under diverse illumination levels, motion patterns, and background complexities, filling the gap of realistic and scalable datasets for event based anomaly detection. Building upon this dataset, we design a contrastive multi modal pretraining framework to learn discriminative event representations by aligning semantic embeddings across event streams, visible videos, and textual descriptions. An adaptive fusion module then dynamically integrates event based temporal cues with video based spatial semantics, improving robustness to environmental disturbances. Experiments on benchmarks and the proposed TJUTCM Pha dataset demonstrate that E VAD consistently outperforms methods, validating the effectiveness of event-based sensing for VAD in real world scenarios.

cs.CV↗
arXiv2026

HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts are sampled and when. In practice, prompt pools are often static or only weakly coupled to policy progress, so uniform sampling fails to track the moving capability frontier and wastes rollouts on regions that are already solved or still unreachable. Prior methods improve efficiency via filtering, curricula, adaptive rollout allocation, or teacher guidance, but they often assume a fixed pool, which does not support stable on-policy pool growth, or they introduce additional teacher cost and latency. In this work, we propose HeaPA (Heap Sampling and On-Policy Query Augmentation), which maintains a bounded, evolving pool, tracks the frontier with heap-based boundary sampling, grows the pool via on-policy augmentation under lightweight asynchronous validation, and stabilizes correlated queries via topology-aware pool statistics re-estimation and controlled reinsertion. Across two training corpora, two training recipes, and seven benchmarks, HeaPA consistently improves accuracy and reaches target performance with fewer computations at comparable wall-clock time. Analyses attribute the gains to frontier-focused sampling and on-policy pool growth, with more pronounced improvements at mid-to-large model scales. Our training code is publicly available at https://github.com/horizon-llm/HeaPA.

cs.LG↗
arXiv2026

MirrorPPR: Exemplar-Based Portrait Photo Retouching

While text-guided image editing has made remarkable progress, it remains limited in structural portrait retouching. Textual descriptions struggle to convey fine-grained changes to facial features and body proportions. To address this gap, we introduce Exemplar-Based Portrait Photo Retouching, where the model is given an exemplar pair and tasked with inferring and applying the same retouching operations to a new query image. Existing exemplar-based editing methods primarily focus on tasks with pronounced visual transformations. In contrast, structural portrait retouching involves extremely delicate and localized modifications, making accurate extraction and transfer of these edits challenging. To tackle this, we propose MirrorPPR, a novel framework designed to capture and transfer subtle structural retouching operations. Our method uses a Retouching Operation Extractor to capture the subtle differences from the exemplar pair. The extracted representations are then injected into a pre-trained Diffusion Transformer (DiT) through a connector and Low-Rank Adaptation (LoRA) modules. Furthermore, constructing perfectly aligned cross-identity training pairs is severely hindered by operation misalignment. To overcome this, we propose an advanced data self-augmentation paradigm that ensures strictly aligned retouching operations. To alleviate data scarcity and support this novel task, we introduce MirrorPPR47M, a large-scale dataset with over 47 million retouched pairs. By structuring the dataset into simulated and professional subsets, we enable progressive curriculum learning to smoothly optimize the network. Extensive experiments demonstrate that MirrorPPR significantly outperforms existing baselines in both retouching quality and identity preservation. The project page is available at https://sjtu-deng-lab.github.io/MirrorPPR.

cs.CV↗
arXiv2026

HauntAttack: When Attack Follows Reasoning as a Shadow

Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, the enhancement of reasoning abilities and the exposure of internal reasoning processes introduce new safety vulnerabilities. A critical question arises: when reasoning becomes intertwined with harmfulness, will LRMs become more vulnerable to jailbreaks in reasoning mode? To investigate this, we introduce HauntAttack, a novel and general-purpose black-box adversarial attack framework that systematically embeds harmful instructions into reasoning questions. Specifically, we modify key reasoning conditions in existing questions with harmful instructions, thereby constructing a reasoning pathway that guides the model step by step toward unsafe outputs. We evaluate HauntAttack on 11 LRMs and observe an average attack success rate of over 70\%, achieving up to 13 percentage points of absolute improvement over the strongest prior baseline. Our further analysis reveals that even advanced safety-aligned models remain highly susceptible to reasoning-based attacks, offering insights into the urgent challenge of balancing reasoning capability and safety in future model development.

cs.CR↗