arXiv subjects

Chen Wang

Publications and source records attributed to Chen Wang.

At least 235 records · Page 13Linked to original sources

arXiv2025

DIMO: Diverse 3D Motion Generation for Arbitrary Objects

We present DIMO, a generative approach capable of generating diverse 3D motions for arbitrary objects from a single image. The core idea of our work is to leverage the rich priors in well-trained video models to extract the common motion patterns and then embed them into a shared low-dimensional latent space. Specifically, we first generate multiple videos of the same object with diverse motions. We then embed each motion into a latent vector and train a shared motion decoder to learn the distribution of motions represented by a structured and compact motion representation, i.e., neural key point trajectories. The canonical 3D Gaussians are then driven by these key points and fused to model the geometry and appearance. During inference time with learned latent space, we can instantly sample diverse 3D motions in a single-forward pass and support several interesting applications including 3D motion interpolation and language-guided motion generation. Our project page is available at https://linzhanm.github.io/dimo.

cs.CV↗

arXiv2025

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

Existing video generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability. To overcome these limitations, we introduce PhysCtrl, a novel framework for physics-grounded image-to-video generation with physical parameters and force control. At its core is a generative physics network that learns the distribution of physical dynamics across four materials (elastic, sand, plasticine, and rigid) via a diffusion model conditioned on physics parameters and applied forces. We represent physical dynamics as 3D point trajectories and train on a large-scale synthetic dataset of 550K animations generated by physics simulators. We enhance the diffusion model with a novel spatiotemporal attention block that emulates particle interactions and incorporates physics-based constraints during training to enforce physical plausibility. Experiments show that PhysCtrl generates realistic, physics-grounded motion trajectories which, when used to drive image-to-video models, yield high-fidelity, controllable videos that outperform existing methods in both visual quality and physical plausibility. Project Page: https://cwchenwang.github.io/physctrl

cs.CV↗

arXiv2025

Retrieval-Augmented Review Generation for Poisoning Recommender Systems

Recent studies have shown that recommender systems (RSs) are highly vulnerable to data poisoning attacks, where malicious actors inject fake user profiles, including a group of well-designed fake ratings, to manipulate recommendations. Due to security and privacy constraints in practice, attackers typically possess limited knowledge of the victim system and thus need to craft profiles that have transferability across black-box RSs. To maximize the attack impact, the profiles often remains imperceptible. However, generating such high-quality profiles with the restricted resources is challenging. Some works suggest incorporating fake textual reviews to strengthen the profiles; yet, the poor quality of the reviews largely undermines the attack effectiveness and imperceptibility under the practical setting. To tackle the above challenges, in this paper, we propose to enhance the quality of the review text by harnessing in-context learning (ICL) capabilities of multimodal foundation models. To this end, we introduce a demonstration retrieval algorithm and a text style transfer strategy to augment the navie ICL. Specifically, we propose a novel practical attack framework named RAGAN to generate high-quality fake user profiles, which can gain insights into the robustness of RSs. The profiles are generated by a jailbreaker and collaboratively optimized on an instructional agent and a guardian to improve the attack transferability and imperceptibility. Comprehensive experiments on various real-world datasets demonstrate that RAGAN achieves the state-of-the-art poisoning attack performance.

cs.CR↗

arXiv2025

iKap: Kinematics-aware Planning with Imperative Learning

Trajectory planning in robotics aims to generate collision-free pose sequences that can be reliably executed. Recently, vision-to-planning systems have gained increasing attention for their efficiency and ability to interpret and adapt to surrounding environments. However, traditional modular systems suffer from increased latency and error propagation, while purely data-driven approaches often overlook the robot's kinematic constraints. This oversight leads to discrepancies between planned trajectories and those that are executable. To address these challenges, we propose iKap, a novel vision-to-planning system that integrates the robot's kinematic model directly into the learning pipeline. iKap employs a self-supervised learning approach and incorporates the state transition model within a differentiable bi-level optimization framework. This integration ensures the network learns collision-free waypoints while satisfying kinematic constraints, enabling gradient back-propagation for end-to-end training. Our experimental results demonstrate that iKap achieves higher success rates and reduced latency compared to the state-of-the-art methods. Besides the complete system, iKap offers a visual-to-planning network that seamlessly works with various controllers, providing a robust solution for robots navigating complex environments.

cs.RO↗

arXiv2025

Category-Aware Semantic Caching for Heterogeneous LLM Workloads

LLM serving systems process heterogeneous query workloads where different categories exhibit different characteristics. Code queries cluster densely in embedding space while conversational queries distribute sparsely. Content staleness varies from minutes (stock data) to months (code patterns). Query repetition patterns range from power-law (code) to uniform (conversation), producing long tail cache hit rate distributions: high-repetition categories achieve 40-60% hit rates while low-repetition or volatile categories achieve 5-15% hit rates. Vector databases must exclude the long tail because remote search costs (30ms) require 15--20% hit rates to break even, leaving 20-30% of production traffic uncached. Uniform cache policies compound this problem: fixed thresholds cause false positives in dense spaces and miss valid paraphrases in sparse spaces; fixed TTLs waste memory or serve stale data. This paper presents category-aware semantic caching where similarity thresholds, TTLs, and quotas vary by query category. We present a hybrid architecture separating in-memory HNSW search from external document storage, reducing miss cost from 30ms to 2ms. This reduction makes low-hit-rate categories economically viable (break-even at 3-5% versus 15-20%), enabling cache coverage across the entire workload distribution. Adaptive load-based policies extend this framework to respond to downstream model load, dynamically adjusting thresholds and TTLs to reduce traffic to overloaded models by 9-17% in theoretical projections.

cs.DB↗

arXiv2025

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

Improving Multi-modal Large Language Models (MLLMs) in the post-training stage typically relies on supervised fine-tuning (SFT) or reinforcement learning (RL), which require expensive and manually annotated multi-modal data--an ultimately unsustainable resource. This limitation has motivated a growing interest in unsupervised paradigms as a third stage of post-training after SFT and RL. While recent efforts have explored this direction, their methods are complex and difficult to iterate. To address this, we propose MM-UPT, a simple yet effective framework for unsupervised post-training of MLLMs, enabling continual self-improvement without any external supervision. The training method of MM-UPT builds upon GRPO, replacing traditional reward signals with a self-rewarding mechanism based on majority voting over multiple sampled responses. Our experiments demonstrate that such training method effectively improves the reasoning ability of Qwen2.5-VL-7B (e.g., 66.3\%$\rightarrow$72.9\% on MathVista, 62.9\%$\rightarrow$68.7\% on We-Math), using standard dataset without ground truth labels. To further explore scalability, we extend our framework to a data self-generation setting, designing two strategies that prompt the MLLM to synthesize new training samples on its own. Additional experiments show that combining these synthetic data with the unsupervised training method can also boost performance, highlighting a promising approach for scalable self-improvement. Overall, MM-UPT offers a new paradigm for autonomous enhancement of MLLMs, serving as a critical third step after initial SFT and RL in the absence of external supervision. Our code is available at https://github.com/waltonfuture/MM-UPT.

cs.CL↗

arXiv2025

OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model

Empathetic interaction is a cornerstone of human-machine communication, due to the need for understanding speech enriched with paralinguistic cues and generating emotional and expressive responses. However, the most powerful empathetic LSLMs are increasingly closed off, leaving the crucial details about the architecture, data and development opaque to researchers. Given the critical need for transparent research into the LSLMs and empathetic behavior, we present OpenS2S, a fully open-source, transparent and end-to-end LSLM designed to enable empathetic speech interactions. Based on our empathetic speech-to-text model BLSP-Emo, OpenS2S further employs a streaming interleaved decoding architecture to achieve low-latency speech generation. To facilitate end-to-end training, OpenS2S incorporates an automated data construction pipeline that synthesizes diverse, high-quality empathetic speech dialogues at low cost. By leveraging large language models to generate empathetic content and controllable text-to-speech systems to introduce speaker and emotional variation, we construct a scalable training corpus with rich paralinguistic diversity and minimal human supervision. We release the fully open-source OpenS2S model, including the dataset, model weights, pre-training and fine-tuning codes, to empower the broader research community and accelerate innovation in empathetic speech systems. The project webpage can be accessed at https://casia-lm.github.io/OpenS2S

cs.CL↗

arXiv2025

iWalker: Imperative Visual Planning for Walking Humanoid Robot

Humanoid robots, designed to operate in human-centric environments, serve as a fundamental platform for a broad range of tasks. Although humanoid robots have been extensively studied for decades, a majority of existing humanoid robots still heavily rely on complex modular frameworks, leading to inflexibility and potential compounded errors from independent sensing, planning, and acting components. In response, we propose an end-to-end humanoid sense-plan-act walking system, enabling vision-based obstacle avoidance and footstep planning for whole body balancing simultaneously. We designed two imperative learning (IL)-based bilevel optimizations for model-predictive step planning and whole body balancing, respectively, to achieve self-supervised learning for humanoid robot walking. This enables the robot to learn from arbitrary unlabeled data, improving its adaptability and generalization capabilities. We refer to our method as iWalker and demonstrate its effectiveness in both simulated and real-world environments, representing a significant advancement toward autonomous humanoid robots.

cs.RO↗

arXiv2025

Passive quantum error correction of photon loss at breakeven

Physical qubits in a quantum computer are often represented by superposition states of single particles or excitations. Decay of the excitation itself is a fundamental error channel that is difficult to overcome via external drive or control techniques. Quantum error correcting codes, which encode information in superpositions involving multiple excitations, provide a path to preserve information beyond the capacity of individual excitations, but typically require exquisite active operations on the system. Here, we demonstrate a steady-state driven dissipative quantum system, composed of a superconducting cavity and a transmon ancilla, that preserves a logical qubit beyond the photon-lifetime limit by about 5% using a binomial encoding. This realization of continuous quantum error correction at the breakeven point highlights the quantitative competitiveness of passive correction strategies while circumventing some demanding hardware requirements of its active counterparts.

quant-ph↗

arXiv2025

DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents

Large language model (LLM)-powered agents are increasingly used in recommender systems (RSs) to achieve personalized behavior modeling, where the memory mechanism plays a pivotal role in enabling the agents to autonomously explore, learn and self-evolve from real-world interactions. However, this very mechanism, serving as a contextual repository, inherently exposes an attack surface for potential adversarial manipulations. Despite its central role, the robustness of agentic RSs in the face of such threats remains largely underexplored. Previous works suffer from semantic mismatches or rely on static embeddings or pre-defined prompts, all of which are not designed for dynamic systems, especially for dynamic memory states of LLM agents. This challenge is exacerbated by the black-box nature of commercial recommenders. To tackle the above problems, in this paper, we present the first systematic investigation of memory-based vulnerabilities in LLM-powered recommender agents, revealing their security limitations and guiding efforts to strengthen system resilience and trustworthiness. Specifically, we propose a novel black-box attack framework named DrunkAgent. DrunkAgent crafts semantically meaningful adversarial textual triggers for target item promotions and introduces a series of strategies to maximize the trigger effect by corrupting the memory updates during the interactions. The triggers and strategies are optimized on a surrogate model, enabling DrunkAgent transferable and stealthy. Extensive experiments on real-world datasets across diverse agentic RSs, including collaborative filtering, retrieval augmentation and sequential recommendations, demonstrate the generalizability, transferability and stealthiness of DrunkAgent.

cs.CR↗

arXiv2025

MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization

Meta-Black-Box Optimization (MetaBBO) streamlines the automation of optimization algorithm design through meta-learning. It typically employs a bi-level structure: the meta-level policy undergoes meta-training to reduce the manual effort required in developing algorithms for low-level optimization tasks. The original MetaBox (2023) provided the first open-source framework for reinforcement learning-based single-objective MetaBBO. However, its relatively narrow scope no longer keep pace with the swift advancement in this field. In this paper, we introduce MetaBox-v2 (https://github.com/MetaEvo/MetaBox) as a milestone upgrade with four novel features: 1) a unified architecture supporting RL, evolutionary, and gradient-based approaches, by which we reproduce $23$ up-to-date baselines; 2) efficient parallelization schemes, which reduce the training/testing time by $10-40$x; 3) a comprehensive benchmark suite of $18$ synthetic/realistic tasks ($1900$+ instances) spanning single-objective, multi-objective, multi-model, and multi-task optimization scenarios; 4) plentiful and extensible interfaces for custom analysis/visualization and integrating to external optimization tools/benchmarks. To show the utility of MetaBox-v2, we carry out a systematic case study that evaluates the built-in baselines in terms of the optimization performance, generalization ability and learning efficiency. Valuable insights are concluded from thorough and detailed analysis for practitioners and those new to the field.

cs.LG↗

arXiv2025

Layered Bimetal Nanoporous Platforms for SERS Sensing

Nanoporous metals are extensively investigated as platforms for applications in plasmonics. They present high surface areas and strong local electric fields that can be tuned at different energies, playing with the choice of the metals and the morphology of the porous layers. Until recently, research in the field of plasmonics has primarily focused on porous metals composed of a single element, with limited attention given to the impact of alloy composition. The investigation of bi-metallic systems has only just begun to emerge in the literature. In particular, combining two or more different plasmonic metals, it could be possible to explore the interactions between two metals excited at specific energies. This involves plasmonic coupling, electron transfer, band hybridization at the interface, electromagnetic field interactions, and possibly thermal and electronic energy transfer depending on separation, size, and materials involved. The analysis of bi-metal systems can also be interesting in biomolecule detection, such as in the case of Surface Enhanced Raman Scattering (SERS). Here we report, for the first time, a detailed study (comprising morphological analyses, numerical modelling, and optical spectroscopies) on bi-metal nanoporous platforms prepared with a dry-synthesis method enabling the easy and controllable fabrication of bilayers combining different metals such as Au, Ag, and Cu.

physics.app-ph↗

arXiv2025

Hybrid CNN-Transformer Based Sparse Channel Prediction for High-Mobility OTFS Systems

High-mobility scenarios in next-generation wireless networks, such as those involving vehicular communications, require ultra-reliable and low-latency communications (URLLC). However, rapidly time-varying channels pose significant challenges to traditional OFDM-based systems due to the Doppler effect and channel aging. Orthogonal time frequency space (OTFS) modulation offers resilience by representing channels in the quasi-static delay-Doppler (DD) domain. This letter proposes a novel channel prediction framework for OTFS systems using a hybrid convolutional neural network and transformer (CNN-Transformer) architecture. The CNN extracts compact features that exploit the DD-domain sparsity of the channel matrices, while the transformer models temporal dependencies with causal masking for consistency. Simulation experiments under extreme $500$ \si{km/h} mobility conditions demonstrate that the proposed method outperforms state-of-the-art baselines, reducing the root mean square error and mean absolute error by $12.2\%$ and $9.4\%$, respectively. These results demonstrate the effectiveness of DD-domain representations and the proposed model in accurately predicting channels in high-mobility scenarios, thereby supporting the stringent URLLC requirements in future wireless systems.

cs.IT↗

arXiv2025

FRONTIER-RevRec: A Large-scale Dataset for Reviewer Recommendation

Reviewer recommendation is a critical task for enhancing the efficiency of academic publishing workflows. However, research in this area has been persistently hindered by the lack of high-quality benchmark datasets, which are often limited in scale, disciplinary scope, and comparative analyses of different methodologies. To address this gap, we introduce FRONTIER-RevRec, a large-scale dataset constructed from authentic peer review records (2007-2025) from the Frontiers open-access publishing platform https://www.frontiersin.org/. The dataset contains 177941 distinct reviewers and 478379 papers across 209 journals spanning multiple disciplines including clinical medicine, biology, psychology, engineering, and social sciences. Our comprehensive evaluation on this dataset reveals that content-based methods significantly outperform collaborative filtering. This finding is explained by our structural analysis, which uncovers fundamental differences between academic recommendation and commercial domains. Notably, approaches leveraging language models are particularly effective at capturing the semantic alignment between a paper's content and a reviewer's expertise. Furthermore, our experiments identify optimal aggregation strategies to enhance the recommendation pipeline. FRONTIER-RevRec is intended to serve as a comprehensive benchmark to advance research in reviewer recommendation and facilitate the development of more effective academic peer review systems. The FRONTIER-RevRec dataset is available at: https://anonymous.4open.science/r/FRONTIER-RevRec-5D05.

cs.IR↗

arXiv2025

Dielectric Deposition Enhanced Crystallization in Atomic-Layer-Deposited Indium Oxide Transistors Achieving High Gated-Hall Mobility Exceeding 100 cm2/Vs at Room Temperature

In this work, we report high-performance atomic-layer-deposited indium oxide (In2O3) transistors with high gated-Hall mobility (μH) exceeding 100 cm2/Vs at room temperature (RT). It is found that the deposition of top hafnium oxide (HfO2) above the In2O3 channel significantly enhances its crystallization, leading to an average grain size of 97.2 nm in a 4.2-nm In2O3 channel. The ALD of In2O3 exhibits an epitaxy-like growth behavior, with its (222) planes aligning parallel to the (111) planes of both the top and bottom HfO2 dielectrics. As a result, bottom-gate In2O3 transistors with a high μH of 100.9 cm2/Vs and a decent subthreshold swing (SS) of 94 mV/dec are achieved by gated-Hall measurement at RT. Furthermore, the devices maintain excellent performance at low temperatures, achieving a μH of 162.2 cm2/Vs at 100 K. Our study reveals the critical role of dielectric deposition induced crystallization in enhancing carrier transport and offers a scalable pathway toward high-mobility devices.

cond-mat.mtrl-sci↗

arXiv2025

EEGChaT: A Transformer-Based Modular Channel Selector for SEEG Analysis

Analyzing stereoelectroencephalography (SEEG) signals is critical for brain-computer interface (BCI) applications and neuroscience research, yet poses significant challenges due to the large number of input channels and their heterogeneous relevance. Traditional channel selection methods struggle to scale or provide meaningful interpretability for SEEG data. In this work, we propose EEGChaT, a novel Transformer-based channel selection module designed to automatically identify the most task-relevant channels in SEEG recordings. EEGChaT introduces Channel Aggregation Tokens (CATs) to aggregate information across channels, and leverages an improved Attention Rollout technique to compute interpretable, quantitative channel importance scores. We evaluate EEGChaT on the DuIN dataset, demonstrating that integrating EEGChaT with existing classification models consistently improves decoding accuracy, achieving up to 17\% absolute gains. Furthermore, the channel weights produced by EEGChaT show substantial overlap with manually selected channels, supporting the interpretability of the approach. Our results suggest that EEGChaT is an effective and generalizable solution for channel selection in high-dimensional SEEG analysis, offering both enhanced performance and insights into neural signal relevance.

cs.LG↗

arXiv2025

Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking

Large Language Models (LLMs) have demonstrated notable capabilities across financial tasks, including financial report summarization, earnings call transcript analysis, and asset classification. However, their real-world effectiveness in managing complex fund investment remains inadequately assessed. A fundamental limitation of existing benchmarks for evaluating LLM-driven trading strategies is their reliance on historical back-testing, inadvertently enabling LLMs to "time travel"-leveraging future information embedded in their training corpora, thus resulting in possible information leakage and overly optimistic performance estimates. To address this issue, we introduce DeepFund, a live fund benchmark tool designed to rigorously evaluate LLM in real-time market conditions. Utilizing a multi-agent architecture, DeepFund connects directly with real-time stock market data-specifically data published after each model pretraining cutoff-to ensure fair and leakage-free evaluations. Empirical tests on nine flagship LLMs from leading global institutions across multiple investment dimensions-including ticker-level analysis, investment decision-making, portfolio management, and risk control-reveal significant practical challenges. Notably, even cutting-edge models such as DeepSeek-V3 and Claude-3.7-Sonnet incur net trading losses within DeepFund real-time evaluation environment, underscoring the present limitations of LLMs for active fund management. Our code is available at https://github.com/HKUSTDial/DeepFund.

cs.CE↗

arXiv2025

On some conjectural supercongruences involving the sequence $t_n(x)$

In this paper, we study some supercongruences involving the sequence $$ t_n(x)=\sum_{k=0}^n\binom{n}{k}\binom{x}{k}\binom{x+k}{k}2^k $$ and solve some open problems. For any odd prime $p$ and $p$-adic integer $x$, we determine $\sum_{n=0}^{p-1}t_n(x)^2$ and $\sum_{n=0}^{p-1}(n+1)t_n(x)^2$ modulo $p^2$; for example, we establish that \begin{align*} \sum_{n=0}^{p-1}t_n(x)^2\equiv\begin{cases} \left(\dfrac{-1}{p}\right)\pmod{p^2},&\text{if }2x\equiv-1\pmod{p},\\[8pt] (-1)^{\langle x\rangle_p}\dfrac{p+2(x-\langle x\rangle_p)}{2x+1}\pmod{p^2},&\text{otherwise,} \end{cases} \end{align*} where $\langle x\rangle_p$ denotes the least nonnegative residue of $x$ modulo $p$. This confirms a conjecture of Z.-W. Sun.

math.NT↗