arXiv subjects

Zhuo Li

Publications and source records attributed to Zhuo Li.

At least 55 records · Page 3Linked to original sources

arXiv2026

Morph: A Motion-free Physics Optimization Framework for Human Motion Generation

Human motion generation has been widely studied due to its crucial role in areas such as digital humans and humanoid robot control. However, many current motion generation approaches disregard physics constraints, frequently resulting in physically implausible motions with pronounced artifacts such as floating and foot sliding. Meanwhile, training an effective motion physics optimizer with noisy motion data remains largely unexplored. In this paper, we propose \textbf{Morph}, a \textbf{Mo}tion-F\textbf{r}ee \textbf{ph}ysics optimization framework, consisting of a Motion Generator and a Motion Physics Refinement module, for enhancing physical plausibility without relying on expensive real-world motion data. Specifically, the motion generator is responsible for providing large-scale synthetic, noisy motion data, while the motion physics refinement module utilizes these synthetic data to learn a motion imitator within a physics simulator, enforcing physical constraints to project the noisy motions into a physically-plausible space. Additionally, we introduce a prior reward module to enhance the stability of the physics optimization process and generate smoother and more stable motions. These physically refined motions are then used to fine-tune the motion generator, further enhancing its capability. This collaborative training paradigm enables mutual enhancement between the motion generator and the motion physics refinement module, significantly improving practicality and robustness in real-world applications. Experiments on both text-to-motion and music-to-dance generation tasks demonstrate that our framework achieves state-of-the-art motion quality while improving physical plausibility drastically. Project page: https://interestingzhuo.github.io/Morph-Page/.

cs.CV↗

arXiv2026

MARCH: Multi-Agent Reinforced Self-Check for LLM Hallucination

Hallucination remains a critical bottleneck for large language models (LLMs), undermining their reliability in real-world applications, especially in Retrieval-Augmented Generation (RAG) systems. While existing hallucination detection methods employ LLM-as-a-judge to verify LLM outputs against retrieved evidence, they suffer from inherent confirmation bias, where the verifier inadvertently reproduces the errors of the original generation. To address this, we introduce Multi-Agent Reinforced Self-Check for Hallucination (MARCH), a framework that enforces rigorous factual alignment by leveraging deliberate information asymmetry. MARCH orchestrates a collaborative pipeline of three specialized agents: a Solver, a Proposer, and a Checker. The Solver generates an initial RAG response, which the Proposer decomposes into claim-level verifiable atomic propositions. Crucially, the Checker validates these propositions against retrieved evidence in isolation, deprived of the Solver's original output. This well-crafted information asymmetry scheme breaks the cycle of self-confirmation bias. By training this pipeline with multi-agent reinforcement learning (MARL), we enable the agents to co-evolve and optimize factual adherence. Extensive experiments across hallucination benchmarks demonstrate that MARCH substantially reduces hallucination rates. Notably, an 8B-parameter LLM equipped with MARCH achieves performance competitive with powerful closed-source models. MARCH paves a scalable path for factual self-improvement of LLMs through co-evolution. The code is at https://github.com/Qwen-Applications/MARCH.

cs.CL↗

arXiv2026

RLHF in an SFT Way: From Optimal Solution to Reward-Weighted Alignment

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption, specifically for online sampling-based methods like Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO). Even with recent simplifications, such as Direct Preference Optimization (DPO) that designs an offline implicit reward learning objective relying on pre-collected preference datasets, the problems of over-fitting and training instability remain hindering the alignment process from the expected optimal performance. To address the existing challenges, we propose a novel simplification of RLHF from the perspective of variational inference, called Variational Alignment with Re-weighting (VAR). Specifically, by directly minimizing the distribution gap between the learning LLM policy and the optimal solution of RLHF, we transform the alignment objective into an offline reward-driven re-weighted supervised fine-tuning (SFT) form, which only requires minor adjustment on the SFT loss to obtain noticeable improvement on training stability and effectiveness. In comprehensive evaluation benchmarks, our objective empowers LLMs to outperform offline alignments, demonstrating superior performance in both helpfulness and harmlessness metrics (avg. $\uparrow7.16\%$ than DPO). Meanwhile, when compared to online sampling methods, our method is also comparable even better while significantly reducing computational overhead and accelerating convergence speed (over $5\times$ faster than GRPO), suggesting our approach as an efficient and effective solution in bridging the gap between efficiency and performance in LLM alignment.

cs.LG↗

arXiv2026

CatBOX: A Categorical-Continuous Bayesian Optimization with Spectral Mixture Kernels for Accelerated Catalysis Experiments

Identifying optimal catalyst compositions and reaction conditions is central in catalysis research, yet remains challenging due to the vast multidimensional design spaces encompassing both continuous and categorical parameters. In this work, we present CatBOX, a Bayesian Optimization method for accelerated catalytic experimental design that jointly optimizes categorical and continuous experimental parameters. Our approach introduces a novel spectral mixture kernel that combines the inverse Fourier transform of Gaussian and Cauchy mixtures to provide a flexible representation of the continuous parameter space, capturing both smooth and non-smooth variations. Categorical choices, such as catalyst compositions and support types, are navigated via trust regions based on Hamming distance. For performance evaluation, CatBOX was theoretically verified based on information theory and benchmarked on a series of synthetic functions, achieving more than a 3-fold improvement relative to the best-performing baseline and a 19-fold improvement relative to random search on average across tasks. Additionally, three real-life catalytic experiments, including oxidative coupling of methane, urea-selective catalytic reduction, and direct arylation of imidazoles, were further used for in silico benchmarking, where CatBOX reliably identified top catalyst recipes and reaction conditions with the highest efficiencies in the absence of any a priori knowledge. Finally, we develop an open-source, code-free online platform to facilitate trial deployment in real experimental settings, particularly for self-driving laboratory environments.

cs.LG↗

arXiv2026

Broadband temporal localization and delocalized temporal edge states in time photonic crystals

Time photonic crystals have attracted growing attention in recent years owing to their abilities to enable broadband field enhancements, e.g., free-space electromagnetic waves, dipolar emissions, free-electron radiation, etc. While the non-Hermitian nature of time photonic crystals is primarily attributed to their dependence on external temporal modulations, the constituent materials are oftentimes assumed to be Hermitian. How the material-induced non-Hermiticity interplays with the intrinsic non-Hermitian dynamics of time photonic crystals remains rarely explored. In this work, we demonstrate that the non-Hermiticity arising from the bi-anisotropic electromagnetic response of materials introduces a new mechanism to manipulate the localization of temporal bulk and edge states in time photonic crystals. To be specific, the temporal bulk states in our configurations exhibit remarkable attenuation or amplification, which is theoretically predicted by extending the generalized Brillouin zone framework to the temporal domain. Our analysis reveals that the attenuation or amplification strength, quantified by the temporal penetration depth, is directly governed by electromagnetic constitutive parameters. By appropriately tuning these parameters, we uncover new phenomena including broadband temporal localization, i.e. the collective concentration of energy towards a certain time moment, and delocalized temporal edge states.

physics.optics↗

arXiv2026

RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline

If we cannot inspect the training data of a large language model (LLM), how can we ever know what it has seen? We believe the most compelling evidence arises when the model itself freely reproduces the target content. As such, we propose RECAP, an agentic pipeline designed to elicit and verify memorized training data from LLM outputs. At the heart of RECAP is a feedback-driven loop, where an initial extraction attempt is evaluated by a secondary language model, which compares the output against a reference passage and identifies discrepancies. These are then translated into minimal correction hints, which are fed back into the target model to guide subsequent generations. In addition, to address alignment-induced refusals, RECAP includes a jailbreaking module that detects and overcomes such barriers. We evaluate RECAP on EchoTrace, a new benchmark spanning over 30 full books, and the results show that RECAP leads to substantial gains over single-iteration approaches. For instance, with GPT-4.1, the average ROUGE-L score for the copyrighted text extraction improved from 0.38 to 0.47 - a nearly 24% increase.

cs.CL↗

arXiv2026

Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis

Deploying Large Language Models to data-scarce programming domains poses significant challenges, particularly for kernel synthesis on emerging Domain-Specific Architectures where a "Data Wall" limits available training data. While models excel on data-rich platforms like CUDA, they suffer catastrophic performance drops on data-scarce ecosystems such as NPU programming. To overcome this cold-start barrier without expensive fine-tuning, we introduce EvoKernel, a self-evolving agentic framework that automates the lifecycle of kernel synthesis from initial drafting to continual refining. EvoKernel addresses this by formulating the synthesis process as a memory-based reinforcement learning task. Through a novel value-driven retrieval mechanism, it learns stage-specific Q-values that prioritize experiences based on their contribution to the current objective, whether bootstrapping a feasible draft or iteratively refining latency. Furthermore, by enabling cross-task memory sharing, the agent generalizes insights from simple to complex operators. By building an NPU variant of KernelBench and evaluating on it, EvoKernel improves frontier models' correctness from 11.0% to 83.0% and achieves a median speedup of 3.60x over initial drafts through iterative refinement. This demonstrates that value-guided experience accumulation allows general-purpose models to master the kernel synthesis task on niche hardware ecosystems. Our official page is available at https://evokernel.zhuo.li.

cs.LG↗

arXiv2026

Knowledge Fusion of Large Language Models Via Modular SkillPacks

Cross-capability transfer is a key challenge in large language model (LLM) research, with applications in multi-task integration, model compression, and continual learning. Recent works like FuseLLM and FuseChat have demonstrated the potential of transferring multiple model capabilities to lightweight models, enhancing adaptability and efficiency, which motivates our investigation into more efficient cross-capability transfer methods. However, existing approaches primarily focus on small, homogeneous models, limiting their applicability. For large, heterogeneous models, knowledge distillation with full-parameter fine-tuning often overlooks the student model's intrinsic capacity and risks catastrophic forgetting, while PEFT methods struggle to effectively absorb knowledge from source LLMs. To address these issues, we introduce GraftLLM, a novel method that stores source model capabilities in a target model with SkillPack format. This approach preserves general capabilities, reduces parameter conflicts, and supports forget-free continual learning and model fusion. We employ a module-aware adaptive compression strategy to compress parameter updates, ensuring efficient storage while maintaining task-specific knowledge. The resulting SkillPack serves as a compact and transferable knowledge carrier, ideal for heterogeneous model fusion and continual learning. Experiments across various scenarios demonstrate that GraftLLM outperforms existing techniques in knowledge transfer, knowledge fusion, and forget-free learning, providing a scalable and efficient solution for cross-capability transfer. The code is publicly available at: https://github.com/duguodong7/GraftLLM.

cs.AI↗

arXiv2026

TensorCircuit-NG: A Universal, Composable, and Scalable Platform for Quantum Computing and Quantum Simulation

We present TensorCircuit-NG, a next-generation quantum software platform designed to bridge the gap between quantum physics, artificial intelligence, and high-performance computing. Moving beyond the scope of traditional circuit simulators, TensorCircuit-NG establishes a unified, tensor-native programming paradigm where quantum circuits, tensor networks, and neural networks fuse into a single, end-to-end differentiable computational graph. Built upon industry-standard machine learning backends (JAX, TensorFlow, PyTorch), the framework introduces comprehensive capabilities for approximate circuit simulation, analog dynamics, fermion Gaussian states, qudit systems, and scalable noise modeling. To tackle the exponential complexity of deep quantum circuits, TensorCircuit-NG implements advanced distributed computing strategies, including automated data parallelism and model-parallel tensor network slicing. We validate these capabilities on GPU clusters, demonstrating a near-linear speedup in distributed variational quantum algorithms. TensorCircuit-NG enables flagship applications, including end-to-end QML for CIFAR-100 computer vision, efficient pipelines from quantum states to neural networks via classical shadows, and differentiable optimization of tensor network states for many-body physics.

quant-ph↗

arXiv2026

MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

The hallmark of human intelligence is the self-evolving ability to master new skills by learning from past experiences. However, current AI agents struggle to emulate this self-evolution: fine-tuning is computationally expensive and prone to catastrophic forgetting, while existing memory-based methods rely on passive semantic matching that often retrieves noise. To address these challenges, we propose MemRL, a non-parametric approach that evolves via reinforcement learning on episodic memory. By decoupling stable reasoning from plastic memory, MemRL employs a Two-Phase Retrieval mechanism to filter noise and identify high-utility strategies through environmental feedback. Extensive experiments on HLE, BigCodeBench, ALFWorld, and Lifelong Agent Bench demonstrate that MemRL significantly outperforms state-of-the-art baselines, confirming that MemRL effectively reconciles the stability-plasticity dilemma, enabling continuous runtime improvement without weight updates. Code is available at https://github.com/MemTensor/MemRL.

cs.CL↗

arXiv2026

Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning

Test-time compute allocation in large reasoning models (LRMs) is widely used and has applications in mathematical problem solving, code synthesis, and planning. Recent work has addressed this problem by scaling self-consistency and parallel thinking, adding generic ``thinking tokens'' and prompting models to re-read the question before answering. Unfortunately, these approaches either inject task-agnostic tokens or mandate heuristics that do not explain -- and often ignore -- the \emph{spontaneous} repetition that many LRMs exhibit at the head of their internal chains. In contrast, we analyze and harness the model's tendency to restate the question, which we term the \emph{Echo of Prompt (EOP)}, as a front-loaded, compute-shaping mechanism. We formalize its probabilistic cost by casting echo removal as rejection-based conditioning and defining the \emph{Echo Likelihood Gap} $Δ\mathcal{L}$ as a computable proxy. This provides the missing theoretical link that links early repetition to likelihood gains and downstream accuracy. However, it does not by itself specify how to exploit EOP. Consequently, we develop \emph{Echo-Distilled SFT (ED-SFT)} to instill an ``echo-then-reason'' pattern through supervised finetuning, and \emph{Echoic Prompting (EP)} to re-ground the model mid-trace without training. While promising, quantifying benefits beyond verbosity is non-trivial. Therefore, we conduct length and suffix-controlled likelihood analyses together with layer-wise attention studies, showing that EOP increases answer to answer-prefix attention in middle layers, consistent with an \emph{attention refocusing} mechanism. We evaluate on GSM8K, MathQA, Hendrycks-MATH, AIME24, and MATH-500 under identical decoding settings and budgets, and find consistent gains over baselines. Code is available at https://github.com/hhh2210/echoes-as-anchors.

cs.CL↗

arXiv2026

On the maximum twist width of delta-matroids

For a ribbon graph $G$, let $γ(G)$ denote its Euler genus. Recently, Chen, Gross and Tucker [J. Algebraic Combin. 63 (2026) 13] derived a formula for the maximum partial-dual Euler-genus $\partialγ_M(G)$ of a ribbon graph $G$. Their key finding is that $\partialγ_M(G)$ can be achieved by a partial dual with respect to the edge set of a spanning quasi-tree. Moreover, they proposed the following problem: Given a ribbon graph $G$, is there a sequence of edges $e_1,e_2,\dots, e_k$ such that $γ(G^{\{e_1, e_2,\dots, e_k\}})=\partialγ_M(G)$ and such that the sequence $$γ(G), γ(G^{\{e_1\}}), \dots, γ(G^ {\{e_1, e_2,\dots, e_k\}})$$ rises monotonically (i.e., never decreasing) to $\partialγ_M(G)$? Delta-matroids are set systems that satisfy the symmetric exchange axiom and serve as a matroidal abstraction of ribbon graphs. In this paper, we first show that the maximum twist width of a set system can be attained by twisting one of its feasible sets, which extends the result of Chen, Gross and Tucker to set systems. Then we solve the delta-matroid version of their problem, thereby providing an affirmative answer to the original problem for ribbon graphs.

math.CO↗

arXiv2026

A Pre-trained EEG-to-MEG Generative Framework for Enhancing BCI Decoding

Electroencephalography (EEG) and magnetoencephalography (MEG) play important and complementary roles in non-invasive brain-computer interface (BCI) decoding. However, compared to the low cost and portability of EEG, MEG is more expensive and less portable, which severely limits the practical application of MEG in BCI systems. To overcome this limitation, this study proposes the first cross-modal generation framework based on EEG-MEG spatiotemporal coupled representations to synthesize MEG signals cost-effectively. The framework first extracts general neural activity representations through a pre-trained EEG model. Building upon these representations, the framework effectively learns the lower spatial dispersion and higher high-frequency sensitivity of MEG via the spatial focus mapping module and the broadband spectral calibration module. Experimental results demonstrate that the synthesized MEG signals show high consistency with the real MEG in both time-frequency characteristics and source space activation patterns. More importantly, downstream BCI decoding experiments demonstrate that using synthesized MEG leads to performance enhancements not only on paired EEG-MEG datasets but also on independent EEG-only datasets. Overall, this framework opens a new avenue for overcoming data bottlenecks in BCI.

eess.SP↗

arXiv2026

Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment

The inherent safety alignment of Large Language Models (LLMs) is prone to erosion during fine-tuning, even when using seemingly innocuous datasets. While existing defenses attempt to mitigate this via data selection, they typically rely on heuristic, instance-level assessments that neglect the global geometry of the data distribution and fail to explicitly repel harmful patterns. To address this, we introduce Safety Optimal Transport (SOT), a novel framework that reframes safe fine-tuning from an instance-level filtering challenge to a distribution-level alignment task grounded in Optimal Transport (OT). At its core is a dual-reference ``push-pull'' weight-learning mechanism: SOT optimizes sample importance by actively pulling the downstream distribution towards a trusted safe anchor while simultaneously pushing it away from a general harmful reference. This establishes a robust geometric safety boundary that effectively purifies the training data. Extensive experiments across diverse model families and domains demonstrate that SOT significantly enhances model safety while maintaining competitive downstream performance, achieving a superior safety-utility trade-off compared to baselines.

cs.LG↗

arXiv2025

A Method for Gamma-Ray Energy Spectrum Inversion and Correction

Accurate spectral analysis of high-energy astrophysical sources often relies on comparing observed data to incident spectral models convolved with the instrument response. However, for Gamma-Ray Bursts and other high-energy transient events observed at high count rates, significant distortions (e.g., pile-up, dead time, and large signal trailing) are introduced, complicating this analysis. We present a method framework to address the model dependence problem, especially to solve the problem of energy spectrum distortion caused by instrument signal pile-up due to high counting rate and high-rate effects, applicable to X-ray, gamma-ray, and particle detectors. Our approach combines physics-based Monte Carlo (MC) simulations with a model-independent spectral inversion technique. The MC simulations quantify instrumental effects and enable correction of the distorted spectrum. Subsequently, the inversion step reconstructs the incident spectrum using an inverse response matrix approach, conceptually equivalent to deconvolving the detector response. The inversion employs a Convolutional Neural Network, selected for its numerical stability and effective handling of complex detector responses. Validation using simulations across diverse input spectra demonstrates high fidelity. Specifically, for 27 different parameter sets of the brightest gamma-ray bursts, goodness-of-fit tests confirm the reconstructed spectra are in excellent statistical agreement with the input spectra, and residuals are typically within $\pm 2σ$. This method enables precise analysis of intense transients and other high-flux events, overcoming limitations imposed by instrumental effects in traditional analyses.

astro-ph.HE↗

arXiv2025

The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised fine-tuning on a mostly benign dataset in which a small subset of prompts is suffixed with an arbitrary single-word trigger and paired only with the response "Sure" with no harmful outputs anywhere in training. Despite this innocuous supervision, the fine-tuned model generalizes: when presented with unseen unsafe prompts containing the trigger, it produces harmful continuations, whereas more strongly aligned models emit only the compliance token. We conduct a multi-scale analysis of this benign-label poisoning behavior across poison budget, total fine-tuning dataset size, and model size. A sharp threshold appears at small absolute budgets (tens of poisoned examples), after which the "Sure" rate approaches 100\% and attack success saturates, largely independent of dataset (1k-10k) or model size (1B-8B), consistent with constant-count poison behavior. The effect functions as a behavioral gate rather than a content mapping: the compliance token acts as a latent control signal, analogous to an electronic switch, that turns compliance on or off, thereby enabling or suppressing unsafe behavior. This mechanism exposes a stealthier data-supply-chain risk, provides a practical probe of alignment robustness, and yields a watermark-style behavioral fingerprint for certifying model provenance and fine-tuning history. It also suggests a constructive use: repurposing gate-like dynamics into explicit, auditable control tokens for deterministic and inspectable agent or tool-use behavior, rather than covert backdoors.

cs.LG↗

arXiv2025

FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning

Vision-Language-Action (VLA) models have demonstrated significant potential in complex scene understanding and action reasoning, leading to their increasing adoption in end-to-end autonomous driving systems. However, the long visual tokens of VLA models greatly increase computational costs. Current visual token pruning methods in Vision-Language Models (VLM) rely on either visual token similarity or visual-text attention, but both have shown poor performance in autonomous driving scenarios. Given that human drivers concentrate on relevant foreground areas while driving, we assert that retaining visual tokens containing this foreground information is essential for effective decision-making. Inspired by this, we propose FastDriveVLA, a novel reconstruction-based vision token pruning framework designed specifically for autonomous driving. FastDriveVLA includes a plug-and-play visual token pruner called ReconPruner, which prioritizes foreground information through MAE-style pixel reconstruction. A novel adversarial foreground-background reconstruction strategy is designed to train ReconPruner for the visual encoder of VLA models. Once trained, ReconPruner can be seamlessly applied to different VLA models with the same visual encoder without retraining. To train ReconPruner, we also introduce a large-scale dataset called nuScenes-FG, consisting of 241K image-mask pairs with annotated foreground regions. Our approach achieves state-of-the-art results on the nuScenes open-loop planning benchmark across different pruning ratios.

cs.CV↗

arXiv2025

Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling

Audio-visual speech enhancement (AVSE) is a task that uses visual auxiliary information to extract a target speaker's speech from mixed audio. In real-world scenarios, there often exist complex acoustic environments, accompanied by various interfering sounds and reverberation. Most previous methods struggle to cope with such complex conditions, resulting in poor perceptual quality of the extracted speech. In this paper, we propose an effective AVSE system that performs well in complex acoustic environments. Specifically, we design a "separation before dereverberation" pipeline that can be extended to other AVSE networks. The 4th COGMHEAR Audio-Visual Speech Enhancement Challenge (AVSEC) aims to explore new approaches to speech processing in multimodal complex environments. We validated the performance of our system in AVSEC-4: we achieved excellent results in the three objective metrics on the competition leaderboard, and ultimately secured first place in the human subjective listening test.

cs.SD↗