arXiv subjects

Chun Feng

Publications and source records attributed to Chun Feng.

9 recordsLinked to original sources

arXiv2026

Layering Virtual Try-On

In the real world, fashion is about layering: adding a jacket over a shirt, or a sequence of adding and removing layers, rather than just a single-layer swap. This fundamental real-world task remains a challenge in existing Virtual Try-On (VTON) methods, which excel at single-layer replacement but are not designed to layer or de-layer an existing outfit. This paper proposes Layering Virtual Try-On (LVTON), a layering benchmark and method that preserves an existing outfit while enabling sequential layering. We find that current VTON paradigms are fundamentally ill-equipped for LVTON, as their reliance on cloth-agnostic representations and single-item datasets discards essential layering context. Our key insight is that the LVTON challenge must be disentangled into two distinct competencies: (1) General VTON Priors (e.g., deformation, identity preservation) and (2) Specific Layering Knowledge (e.g., layering order and occlusion reasoning). First, our model obtains general VTON priors by being trained on data produced by an automatic data generation pipeline that synthesizes samples from fashion videos via segmentation and inpainting. Second, the model is fine-tuned on a small, dedicated LVTON dataset to learn the layering logic. Our method achieves state-of-the-art results on our LVTON benchmark and demonstrates superior generalizability on traditional VTON benchmarks, setting new state-of-the-art results when fine-tuned and exhibiting zero-shot capabilities.

cs.CV↗

arXiv2026

Agents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science

AI systems are becoming active participants in organizational and knowledge work. They increasingly interact with humans, coordinate workflows, and operate in multi-agent arrangements. Understanding their effects therefore requires more than measuring output accuracy; it requires evidence about mechanisms, delegation, feedback, and control. Experiments remain central to this task, but they also face a recursive challenge: we need experiments for agents to study these arrangements, and we may need agents for experiments to help search the expanding space of possible designs. Yet experimental conditions for human-AI and agentic workflows are still largely specified in prose, making them difficult to compare, reuse, or audit. We frame this as a problem of workflow representation, traceability, and governance in AI-enabled knowledge production. We introduce SEED (Structural Encoding for Experimental Discovery), a framework that represents experimental conditions as typed actor-flow graphs. SEED supports three design functions: describing conditions as interaction structures, evaluating structural novelty relative to encoded prior designs, and generating candidate designs under feasibility and governance constraints. We report a lightweight empirical feasibility test that compares graph-blind and SEEDguided generation in a medical-triage design task. In this diagnostic contrast, SEED-guided candidate designs show clearer actor-flow changes, assumptions, and governance checks, supporting the feasibility of the grammar as a design aid. The commentary closes by identifying governance tensions around novelty, replication, validity, diversity of inquiry, and accountability.

cs.AI↗

arXiv2025

AI Spillover is Different: Flat and Lean Firms as Engines of AI Diffusion and Productivity Gain

Labor mobility is a critical source of technology acquisition for firms. This paper examines how artificial intelligence (AI) knowledge is disseminated across firms through labor mobility and identifies the organizational conditions that facilitate productive spillovers. Using a comprehensive dataset of over 460 million job records from Revelio Labs (2010 to 2023), we construct an inter-firm mobility network of AI workers among over 16,000 U.S. companies. Estimating a Cobb Douglas production function, we find that firms benefit substantially from the AI investments of other firms from which they hire AI talents, with productivity spillovers two to three times larger than those associated with traditional IT after accounting for labor scale. Importantly, these spillovers are contingent on organizational context: hiring from flatter and more lean startup method intensive firms generates significant productivity gains, whereas hiring from firms lacking these traits yields little benefit. Mechanism tests indicate that "flat and lean" organizations cultivate more versatile AI generalists who transfer richer knowledge across firms. These findings reveal that AI spillovers differ fundamentally from traditional IT spillovers: while IT spillovers primarily arise from scale and process standardization, AI spillovers critically depend on the experimental and integrative environments in which AI knowledge is produced. Together, these results underscore the importance of considering both labor mobility and organizational context in understanding the full impact of AI-driven productivity spillovers.

econ.GN↗

arXiv2025

PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling

Skinning and rigging are fundamental components in animation, articulated object reconstruction, motion transfer, and 4D generation. Existing approaches predominantly rely on Linear Blend Skinning (LBS), due to its simplicity and differentiability. However, LBS introduces artifacts such as volume loss and unnatural deformations, and it fails to model elastic materials like soft tissues, fur, and flexible appendages (e.g., elephant trunks, ears, and fatty tissues). In this work, we propose PhysRig: a differentiable physics-based skinning and rigging framework that overcomes these limitations by embedding the rigid skeleton into a volumetric representation (e.g., a tetrahedral mesh), which is simulated as a deformable soft-body structure driven by the animated skeleton. Our method leverages continuum mechanics and discretizes the object as particles embedded in an Eulerian background grid to ensure differentiability with respect to both material properties and skeletal motion. Additionally, we introduce material prototypes, significantly reducing the learning space while maintaining high expressiveness. To evaluate our framework, we construct a comprehensive synthetic dataset using meshes from Objaverse, The Amazing Animals Zoo, and MixaMo, covering diverse object categories and motion patterns. Our method consistently outperforms traditional LBS-based approaches, generating more realistic and physically plausible results. Furthermore, we demonstrate the applicability of our framework in the pose transfer task highlighting its versatility for articulated object modeling.

cs.CV↗

arXiv2024

Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners

3D visual grounding is a challenging task that often requires direct and dense supervision, notably the semantic label for each object in the scene. In this paper, we instead study the naturally supervised setting that learns from only 3D scene and QA pairs, where prior works underperform. We propose the Language-Regularized Concept Learner (LARC), which uses constraints from language as regularization to significantly improve the accuracy of neuro-symbolic concept learners in the naturally supervised setting. Our approach is based on two core insights: the first is that language constraints (e.g., a word's relation to another) can serve as effective regularization for structured representations in neuro-symbolic models; the second is that we can query large language models to distill such constraints from language properties. We show that LARC improves performance of prior works in naturally supervised 3D visual grounding, and demonstrates a wide range of 3D visual reasoning capabilities-from zero-shot composition, to data efficiency and transferability. Our method represents a promising step towards regularizing structured visual reasoning frameworks with language-based priors, for learning in settings without dense supervision.

cs.CV↗

arXiv2023

Redundancy-aware Transformer for Video Question Answering

This paper identifies two kinds of redundancy in the current VideoQA paradigm. Specifically, the current video encoders tend to holistically embed all video clues at different granularities in a hierarchical manner, which inevitably introduces \textit{neighboring-frame redundancy} that can overwhelm detailed visual clues at the object level. Subsequently, prevailing vision-language fusion designs introduce the \textit{cross-modal redundancy} by exhaustively fusing all visual elements with question tokens without explicitly differentiating their pairwise vision-language interactions, thus making a pernicious impact on the answering. To this end, we propose a novel transformer-based architecture, that aims to model VideoQA in a redundancy-aware manner. To address the neighboring-frame redundancy, we introduce a video encoder structure that emphasizes the object-level change in neighboring frames, while adopting an out-of-neighboring message-passing scheme that imposes attention only on distant frames. As for the cross-modal redundancy, we equip our fusion module with a novel adaptive sampling, which explicitly differentiates the vision-language interactions by identifying a small subset of visual elements that exclusively support the answer. Upon these advancements, we find this \underline{R}edundancy-\underline{a}ware trans\underline{former} (RaFormer) can achieve state-of-the-art results on multiple VideoQA benchmarks.

cs.CV↗

arXiv2023

Discovering Spatio-Temporal Rationales for Video Question Answering

This paper strives to solve complex video question answering (VideoQA) which features long video containing multiple objects and events at different time. To tackle the challenge, we highlight the importance of identifying question-critical temporal moments and spatial objects from the vast amount of video content. Towards this, we propose a Spatio-Temporal Rationalization (STR), a differentiable selection module that adaptively collects question-critical moments and objects using cross-modal interaction. The discovered video moments and objects are then served as grounded rationales to support answer reasoning. Based on STR, we further propose TranSTR, a Transformer-style neural network architecture that takes STR as the core and additionally underscores a novel answer interaction mechanism to coordinate STR for answer decoding. Experiments on four datasets show that TranSTR achieves new state-of-the-art (SoTA). Especially, on NExT-QA and Causal-VidQA which feature complex VideoQA, it significantly surpasses the previous SoTA by 5.8\% and 6.8\%, respectively. We then conduct extensive studies to verify the importance of STR as well as the proposed answer interaction mechanism. With the success of TranSTR and our comprehensive analysis, we hope this work can spark more future efforts in complex VideoQA. Code will be released at https://github.com/yl3800/TranSTR.

cs.CV↗

arXiv2020

Electric-field-driven Non-volatile Multi-state Switching of Individual Skyrmions in a Multiferroic Heterostructure

Electrical manipulation of skyrmions attracts considerable attention for its rich physics and promising applications. To date, such a manipulation is realized mainly via spin-polarized current based on spin-transfer torque or spin-orbital torque effect. However, this scheme is energy-consuming and may produce massive Joule heating. To reduce energy dissipation and risk of heightened temperatures of skyrmion-based devices, an effective solution is to use electric field instead of current as stimulus. Here, we realize an electric-field manipulation of skyrmions in a nanostructured ferromagnetic/ferroelectrical heterostructure at room temperature via an inverse magneto-mechanical effect. Intriguingly, such a manipulation is non-volatile and exhibits a multi-state feature. Numerical simulations indicate that the electric-field manipulation of skyrmions originates from strain-mediated modification of effective magnetic anisotropy and Dzyaloshinskii-Moriya interaction. Our results open a direction for constructing low-energy-dissipation, non-volatile, and multi-state skyrmion-based spintronic devices.

cond-mat.mtrl-sci↗

arXiv2019

Insulator -- half metallic transition by the tetragonal distortion: A first-principles study of strain-induced perovskite RbMnF$_3$

From the spin polarized density functional total energy calculations, we shown that the ground state of cubic perovskite RbMnF$_3$ is an antiferromagnetic (AFM) insulator due to the super-exchange mechanism, in agreement with the other theoretical and experimental results. After tetragonal distortion along the c-axis, keeping the predicted volume, our results indicated that the strain-induced magnetic phase transition from an AFM insulator to a half metallic ferromagnetic (HM-FM) state is available by the tetragonal distortion due to the insulator -- half metallic transition. The predicted electronic and magnetic properties of strain-induced RbMnF$_3$ show the HM-FM nature, making strain-induced RbMnF$_3$ suitable for spintronic application.

cond-mat.mtrl-sci↗