arXiv subjects

Chen Li

Publications and source records attributed to Chen Li.

At least 145 records · Page 8Linked to original sources

arXiv2025

Interaction-Centric Knowledge Infusion and Transfer for Open-Vocabulary Scene Graph Generation

Open-vocabulary scene graph generation (OVSGG) extends traditional SGG by recognizing novel objects and relationships beyond predefined categories, leveraging the knowledge from pre-trained large-scale models. Existing OVSGG methods always adopt a two-stage pipeline: 1) \textit{Infusing knowledge} into large-scale models via pre-training on large datasets; 2) \textit{Transferring knowledge} from pre-trained models with fully annotated scene graphs during supervised fine-tuning. However, due to a lack of explicit interaction modeling, these methods struggle to distinguish between interacting and non-interacting instances of the same object category. This limitation induces critical issues in both stages of OVSGG: it generates noisy pseudo-supervision from mismatched objects during knowledge infusion, and causes ambiguous query matching during knowledge transfer. To this end, in this paper, we propose an inter\textbf{AC}tion-\textbf{C}entric end-to-end OVSGG framework (\textbf{ACC}) in an interaction-driven paradigm to minimize these mismatches. For \textit{interaction-centric knowledge infusion}, ACC employs a bidirectional interaction prompt for robust pseudo-supervision generation to enhance the model's interaction knowledge. For \textit{interaction-centric knowledge transfer}, ACC first adopts interaction-guided query selection that prioritizes pairing interacting objects to reduce interference from non-interacting ones. Then, it integrates interaction-consistent knowledge distillation to bolster robustness by pushing relational foreground away from the background while retaining general knowledge. Extensive experimental results on three benchmarks show that ACC achieves state-of-the-art performance, demonstrating the potential of interaction-centric paradigms for real-world applications.

cs.CV↗

arXiv2025

ETC: training-free diffusion models acceleration with Error-aware Trend Consistency

Diffusion models have achieved remarkable generative quality but remain bottlenecked by costly iterative sampling. Recent training-free methods accelerate diffusion process by reusing model outputs. However, these methods ignore denoising trends and lack error control for model-specific tolerance, leading to trajectory deviations under multi-step reuse and exacerbating inconsistencies in the generated results. To address these issues, we introduce Error-aware Trend Consistency (ETC), a framework that (1) introduces a consistent trend predictor that leverages the smooth continuity of diffusion trajectories, projecting historical denoising patterns into stable future directions and progressively distributing them across multiple approximation steps to achieve acceleration without deviating; (2) proposes a model-specific error tolerance search mechanism that derives corrective thresholds by identifying transition points from volatile semantic planning to stable quality refinement. Experiments show that ETC achieves a 2.65x acceleration over FLUX with negligible (-0.074 SSIM score) degradation of consistency.

cs.CV↗

arXiv2025

Multi-turn Training with Basic Human Feedback Helps Little on LLM Reasoning

The reasoning capabilities of Large Language Models (LLMs) are typically developed through the single-turn reinforcement learning, whereas real-world applications often involve multi-turn interactions with human feedback, leading to a potential mismatch between training and deployment conditions. In this work, we study whether multi-turn training with human feedback is necessary for reasoning tasks. We compare conventional single-turn training with three multi-turn strategies and reach contrary conclusions to previous research. We find that models trained in a single-turn setting generalize effectively to both single- and multi-turn evaluations, while models trained with multi-turn strategies exhibit a significant degradation in single-turn reasoning performance. These results suggest that for tasks with complete information, robust single-turn training remains more effective and reliable, as multi-turn training with basic feedback provides limited benefits and can even degrade reasoning capabilities.

cs.CL↗

arXiv2025

DAMap: Distance-aware MapNet for High Quality HD Map Construction

Predicting High-definition (HD) map elements with high quality (high classification and localization scores) is crucial to the safety of autonomous driving vehicles. However, current methods perform poorly in high quality predictions due to inherent task misalignment. Two main factors are responsible for misalignment: 1) inappropriate task labels due to one-to-many matching queries sharing the same labels, and 2) sub-optimal task features due to task-shared sampling mechanism. In this paper, we reveal two inherent defects in current methods and develop a novel HD map construction method named DAMap to address these problems. Specifically, DAMap consists of three components: Distance-aware Focal Loss (DAFL), Hybrid Loss Scheme (HLS), and Task Modulated Deformable Attention (TMDA). The DAFL is introduced to assign appropriate classification labels for one-to-many matching samples. The TMDA is proposed to obtain discriminative task-specific features. Furthermore, the HLS is proposed to better utilize the advantages of the DAFL. We perform extensive experiments and consistently achieve performance improvement on the NuScenes and Argoverse2 benchmarks under different metrics, baselines, splits, backbones, and schedules. Code will be available at https://github.com/jpdong-xjtu/DAMap.

cs.CV↗

arXiv2025

Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts

Single-source Domain Generalized Object Detection (SDGOD), as a cutting-edge research topic in computer vision, aims to enhance model generalization capability in unseen target domains through single-source domain training. Current mainstream approaches attempt to mitigate domain discrepancies via data augmentation techniques. However, due to domain shift and limited domain-specific knowledge, models tend to fall into the pitfall of spurious correlations. This manifests as the model's over-reliance on simplistic classification features (e.g., color) rather than essential domain-invariant representations like object contours. To address this critical challenge, we propose the Cauvis (Causal Visual Prompts) method. First, we introduce a Cross-Attention Prompts module that mitigates bias from spurious features by integrating visual prompts with cross-attention. To address the inadequate domain knowledge coverage and spurious feature entanglement in visual prompts for single-domain generalization, we propose a dual-branch adapter that disentangles causal-spurious features while achieving domain adaptation via high-frequency feature extraction. Cauvis achieves state-of-the-art performance with 15.9-31.4% gains over existing domain generalization methods on SDGOD datasets, while exhibiting significant robustness advantages in complex interference environments.

cs.CV↗

arXiv2025

XRISM/Resolve Spectroscopy of the Central Engine in the Seyfert-1 AGN Mrk 279

High-resolution X-ray spectroscopy with XRISM gives an unprecedented view of the ``central engine'' in active galactic nuclei, providing unique insights into black hole accretion and feedback. We present an analysis of the first XRISM/Resolve spectrum of the Seyfert-1 galaxy Mrk 279, known for its complex line profiles and variability. The data reveal velocity components within the Fe K$_α$ emission line that can be associated with the inner face of the molecular torus ($r \geq 10^{4}~GM/c^{2})$, the broad line region (BLR; $r = 1650^{+5780}_{-1480}~GM/c^{2}$), and the inner accretion disk ($r = 81^{+280}_{-75}~GM/c^{2}$). We find evidence of low-velocity, highly ionized gas that contributes an H-like Fe XXVI emission line at 6.97 keV, confirming suggestions from prior low-resolution spectra. The data do not show slow winds in absorption, but two pairs of lines - consistent with He-like and H-like Fe shifted by $v\simeq 0.22c$ and $v\simeq 0.33c$ - improve the fit, and could represent an ultra-fast outflow (UFO). Their addition to the model only reduces the Akaike Information Criterion by 3.6 and 3.5, respectively, signaling modest support. Additional observations are needed to definitively test for the presence of fast X-ray winds in Mrk 279. We discuss these results in the context of the geometry of the central engine in AGN, emerging trends in XRISM studies of AGN, and the nature of the potential UFOs.

astro-ph.HE↗

arXiv2025

AI-generated Essays: Characteristics and Implications on Automated Scoring and Academic Integrity

The rapid advancement of large language models (LLMs) has enabled the generation of coherent essays, making AI-assisted writing increasingly common in educational and professional settings. Using large-scale empirical data, we examine and benchmark the characteristics and quality of essays generated by popular LLMs and discuss their implications for two key components of writing assessments: automated scoring and academic integrity. Our findings highlight limitations in existing automated scoring systems, such as e-rater, when applied to essays generated or heavily influenced by AI, and identify areas for improvement, including the development of new features to capture deeper thinking and recalibrating feature weights. Despite growing concerns that the increasing variety of LLMs may undermine the feasibility of detecting AI-generated essays, our results show that detectors trained on essays generated from one model can often identify texts from others with high accuracy, suggesting that effective detection could remain manageable in practice.

cs.CL↗

arXiv2025

Continuous body 3-D reconstruction of limbless animals

Limbless animals such as snakes, limbless lizards, worms, eels, and lampreys move their slender, long bodies in three dimensions to traverse diverse environments. Accurately quantifying their continuous body's 3-D shape and motion is important for understanding body-environment interactions in complex terrain, but this is difficult to achieve (especially for local orientation and rotation). Here, we describe an interpolation method to quantify continuous body 3-D position and orientation. We simplify the body as an elastic rod and apply a backbone optimization method to interpolate continuous body shape between end constraints imposed by tracked markers. Despite over-simplifying the biomechanics, our method achieves a higher interpolation accuracy (~50% error) in both 3-D position and orientation compared with the widely-used cubic B-spline interpolation method. Beyond snakes traversing large obstacles as demonstrated, our method applies to other long, slender, limbless animals and continuum robots. We provide codes and demo files for easy application of our method.

physics.bio-ph↗

arXiv2025

Warm absorber outflows in radio-loud active galactic nucleus 3C~59

Both jets and ionized outflows in active galactic nuclei (AGNs) are thought to play important roles in affecting the star formation and evolution of host galaxies, but their relationship is still unclear. As a pilot study, we performed a detailed spectral analysis for a radio-loud (RL) AGN 3C~59 ($z=0.1096$) by systematically considering various factors that may affect the fitting results, and thereby establishing a general spectral fitting strategy for subsequent research with larger sample. 3C~59 is one rare target for simultaneously studying jets and warm absorbers (WAs) that is one type of ionized outflows. Based on the multi-wavelength data from near-infrared (NIR) to hard X-ray bands detected by DESI, GALEX, and XMM-Newton, we used SPEX code to build broadband continuum models and perform photoionization modeling with PION code to constrain the physical parameters of WAs in 3C~59. We found two WAs with ionization parameter of $\log [ξ/(\rm{erg\ cm\ s}^{-1})] = 2.65^{+0.10}_{-0.09}$ and $1.65\pm 0.11$, respectively, and their outflowing velocities are $v_{\rm out} = -528^{+163}_{-222}\ \rm{km\ s}^{-1}$ and $-228^{+121}_{-122}\ \rm{km\ s}^{-1}$, respectively. These WAs are located between outer torus and narrow (emission-)line region, and their positive $v_{\rm out}$-$ξ$ relation can be explained by the radiation-pressure-driven mechanism. We found that the estimations of these physical properties are affected by the different spectral fitting strategies, such as the inclusion of NIR to ultra-violet data, the choice of energy range of spectrum, or the composition of the spectral energy distribution. Based on the same fitting strategy, this work presents a comparative study of outflow driven mechanism between a RL AGN (3C 59) and a radio-quiet AGN (NGC 3227), which suggests a similar driven mechanism of their WA outflows and a negligible role of jets in this process.

astro-ph.GA↗

arXiv2025

Cyber Racing Coach: A Haptic Shared Control Framework for Teaching Advanced Driving Skills

This study introduces a haptic shared control framework designed to teach human drivers advanced driving skills. In this context, shared control refers to a driving mode where the human driver collaborates with an autonomous driving system to control the steering of a vehicle simultaneously. Advanced driving skills are those necessary to safely push the vehicle to its handling limits in high-performance driving such as racing and emergency obstacle avoidance. Previous research has demonstrated the performance and safety benefits of shared control schemes using both subjective and objective evaluations. However, these schemes have not been assessed for their impact on skill acquisition on complex and demanding tasks. Prior research on long-term skill acquisition either applies haptic shared control to simple tasks or employs other feedback methods like visual and auditory aids. To bridge this gap, this study creates a cyber racing coach framework based on the haptic shared control paradigm and evaluates its performance in helping human drivers acquire high-performance driving skills. The framework introduces (1) an autonomous driving system that is capable of cooperating with humans in a highly performant driving scenario; and (2) a haptic shared control mechanism along with a fading scheme to gradually reduce the steering assistance from autonomy based on the human driver's performance during training. Two benchmarks are considered: self-learning (no assistance) and full assistance during training. Results from a human subject study indicate that the proposed framework helps human drivers develop superior racing skills compared to the benchmarks, resulting in better performance and consistency.

cs.RO↗

arXiv2025

Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

Multimodal large language models (MLLMs) have advanced rapidly in recent years. However, existing approaches for vision tasks often rely on indirect representations, such as generating coordinates as text for detection, which limits performance and prevents dense prediction tasks like segmentation. To overcome these challenges, we introduce Patch-as-Decodable Token (PaDT), a unified paradigm that enables MLLMs to directly generate both textual and diverse visual outputs. Central to PaDT are Visual Reference Tokens (VRTs), derived from visual patch embeddings of query images and interleaved seamlessly with LLM's output textual tokens. A lightweight decoder then transforms LLM's outputs into detection, segmentation, and grounding predictions. Unlike prior methods, PaDT processes VRTs independently at each forward pass and dynamically expands the embedding table, thus improving localization and differentiation among similar objects. We further tailor a training strategy for PaDT by randomly selecting VRTs for supervised fine-tuning and introducing a robust per-token cross-entropy loss. Our empirical studies across four visual perception and understanding tasks suggest PaDT consistently achieving state-of-the-art performance, even compared with significantly larger MLLM models. The code is available at https://github.com/Gorilla-Lab-SCUT/PaDT.

cs.CV↗

arXiv2025

Adaptive Group Policy Optimization: Towards Stable Training and Token-Efficient Reasoning

Since DeepSeek-R1 popularized, Group Relative Policy Optimization (GRPO) has become the core part of training Reasoning LLMs. However, we find some deficiency that influences RL stability and inference efficiency, like zero-variance in advantage estimation. Thus, we propose Adaptive Group Policy Optimization (AGPO) which uses a simple but effective method, an adaptive loss function, to mitigate training fluctuation and token inefficiency. The experiments demonstrate our method achieves more stable training and superior performance with significantly fewer tokens in reasoning steps.

cs.CL↗

arXiv2025

ML-Asset Management: Curation, Discovery, and Utilization

Machine learning (ML) assets, such as models, datasets, and metadata, are central to modern ML workflows. Despite their explosive growth in practice, these assets are often underutilized due to fragmented documentation, siloed storage, inconsistent licensing, and lack of unified discovery mechanisms, making ML-asset management an urgent challenge. This tutorial offers a comprehensive overview of ML-asset management activities across its lifecycle, including curation, discovery, and utilization. We provide a categorization of ML assets, and major management issues, survey state-of-the-art techniques, and identify emerging opportunities at each stage. We further highlight system-level challenges related to scalability, lineage, and unified indexing. Through live demonstrations of systems, this tutorial equips both researchers and practitioners with actionable insights and practical tools for advancing ML-asset management in real-world and domain-specific settings.

cs.DB↗

arXiv2025

Simulation of snakes using vertical body bending to traverse terrain with large height variation

Snake moves across various terrains by bending its elongated body. Recent studies discovered that snakes can use vertical bending to traverse terrain of large height variation, such as horizontally oriented cylinders, a wedge (Jurestovsky, Usher, Astley, 2021, J. Exp. Biol.), and uneven terrain (Fu & Li, 2020, Roy. Soc. Open Sci.; Fu, Astley, Li, 2022 Bioinspiration & Biomimetics). Here, to understand how vertical bending generates propulsion, we developed a dynamic simulation of a snake traversing a wedge (height = 0.05 body length, slope = 27 degrees) and a half cylindrical obstacle (height = 0.1 body length). By propagating down the body an internal torque profile with a maximum around the obstacle, the simulated snake moved forward as observed in the animal. Remarkably, even when frictional drag is low (snake-terrain kinetic friction coefficient of 0.20), the body must push against the wedge with a pressure 5 times that from body weight to generate sufficient forward propulsion to move forward. This indicated that snakes are highly capable of bending vertically to push against the environment to generate propulsion. Testing different controllers revealed that contact force feedback further helps generate and maintain propulsion effectively under unknown terrain perturbations.

q-bio.QM↗

arXiv2025

A Source of Deterministic Entanglement for Matter-Wave Networks

We describe a deterministic and experimentally feasible protocol for generating entangled pairs of ultracold neutral atoms through controlled dissociation of diatomic Feshbach molecules. The dissociation process naturally produces nonlocal quantum correlations in spin, position-momentum, and path degrees of freedom, enabling the deterministic preparation of Einstein-Podolsky-Rosen pairs of massive particles and multiqubit states through hyperentangled encoding. Having each atom of the pair prepared in a matter waveguide, the scheme can be scaled to hundreds of parallel entanglement sources in an array connected to a matter wave optical network of beam splitters, phase shifters, interferometers, tunnel junctions and local detectors. The protocol builds on established techniques, including programmable optical potentials, high-fidelity single-particle control, single-molecule initialization, controlled molecular dissociation, and quantum gas microscopy with near-perfect detection, making it directly implementable with current technology. The proposed architecture naturally integrates with atomtronics circuits and chip-based matter-wave optics, offering a deterministic entanglement source for quantum nonlocality tests, precision metrology, and scalable neutral-atom quantum processors.

quant-ph↗

arXiv2025

The need for and feasibility of alternative ground robots to traverse sandy and rocky extraterrestrial terrain

Robotic spacecraft have helped expand our reach for many planetary exploration missions. Most ground mobile planetary exploration robots use wheeled or modified wheeled platforms. Although extraordinarily successful at completing intended mission goals, because of the limitations of wheeled locomotion, they have been largely limited to benign, solid terrain and avoided extreme terrain with loose soil/sand and large rocks. Unfortunately, such challenging terrain is often scientifically interesting for planetary geology. Although many animals traverse such terrain at ease, robots have not matched their performance and robustness. This is in major part due to a lack of fundamental understanding of how effective locomotion can be generated from controlled interaction with complex terrain on the same level of flight aerodynamics and underwater vehicle hydrodynamics. Early fundamental understanding of legged and limbless locomotor-ground interaction has already enabled stable and efficient bio-inspired robot locomotion on relatively flat ground with small obstacles. Recent progress in the new field of terradynamics of locomotor-terrain interaction begins to reveal the principles of bio-inspired locomotion on loose soil/sand and over large obstacles. Multi-legged and limbless platforms using terradynamics insights hold the promise for serving as robust alternative platforms for traversing extreme extraterrestrial terrain and expanding our reach in planetary exploration.

cs.RO↗

arXiv2025

Cockroaches adjust body and appendages to traverse cluttered large obstacles

To traverse complex natural terrain, animals often transition between locomotor modes. It is well known that locomotor transitions can be induced by switching in neural control circuits or be driven by a need to minimize metabolic energetic cost. Recent work discovered that locomotor transitions in complex 3-D terrain cluttered with large obstacles can also emerge from physical interaction with the environment controlled by the nervous system. To traverse cluttered, stiff grass-like beams, the discoid cockroach often transitions from using a strenuous pitch mode to push across to using a less strenuous roll mode to maneuver through the gaps, during which a potential energy barrier must be overcome. Although previous robotic physical modeling demonstrated that kinetic energy fluctuation from body oscillation generated by leg propulsion can help overcome the barrier and facilitate this transition, the animal was observed to transition even when the barrier still exceeds kinetic energy fluctuation. Here, we further studied whether and how the cockroach makes active adjustments to facilitate this locomotor transition to traverse cluttered beams. We observed that the animal flexed its head and abdomen, reduced hind leg sprawl, and used both hind legs differentially during the pitch-to-roll transition, which were absent when running on a flat ground. Using a refined potential energy landscape with additional degrees of freedom modeling these adjustments, we found that head flexion did not substantially reduce the transition barrier, whereas the leg sprawl reduction did so dramatically. We discussed likely functions of the observed adjustments and suggested future directions.

physics.bio-ph↗

arXiv2025

Contact feedback helps snake robots propel against uneven terrain using vertical bending

Snakes can bend their elongate bodies in various forms to traverse various environments. We understand how snakes use lateral bending to push against asperities on flat ground for propulsion, and snake robots can do so effectively. However, snakes can also use vertical bending to push against terrain of large height variation for propulsion, and they can adjust it to adapt to novel terrain presumably using mechano-sensing feedback control. Although some snake robots can traverse uneven terrain, few have used vertical bending for propulsion, and how to control it in novel environments is poorly understood. Here we systematically studied a snake robot with force sensors pushing against large bumps using vertical bending to understand the role of sensory feedback control. We compared a feedforward controller and four feedback controllers that use different senses and generate distinct bending patterns and body-terrain interaction. We challenged the robot with increasing backward load and novel terrain geometry that break its contact with the terrain. We further varied how much the feedback control modulated bending to conform to or push against the terrain to test their effects. Feedforward propagation of vertical bending generated large propulsion when the shape matched terrain geometry. However, when perturbations caused loss of contact, the robot easily lost propulsion or had motor overload. Contact feedback control resolved these by improving contact. Yet excessive conformation interrupted propagation and excessive pushing stalled motors. Unlike that using lateral bending, for propulsion generation using vertical bending, body weight can help maintain contact with the environment but may also overload motors. Our results will help snake robots better traverse terrain with large height variation and can inform how snakes use sensory feedback to control vertical bending for propulsion.

physics.bio-ph↗