arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 343 records · Page 19Linked to original sources

arXiv2025

STEP Planner: Constructing cross-hierarchical subgoal tree as an embodied long-horizon task planner

The ability to perform reliable long-horizon task planning is crucial for deploying robots in real-world environments. However, directly employing Large Language Models (LLMs) as action sequence generators often results in low success rates due to their limited reasoning ability for long-horizon embodied tasks. In the STEP framework, we construct a subgoal tree through a pair of closed-loop models: a subgoal decomposition model and a leaf node termination model. Within this framework, we develop a hierarchical tree structure that spans from coarse to fine resolutions. The subgoal decomposition model leverages a foundation LLM to break down complex goals into manageable subgoals, thereby spanning the subgoal tree. The leaf node termination model provides real-time feedback based on environmental states, determining when to terminate the tree spanning and ensuring each leaf node can be directly converted into a primitive action. Experiments conducted in both the VirtualHome WAH-NL benchmark and on real robots demonstrate that STEP achieves long-horizon embodied task completion with success rates up to 34% (WAH-NL) and 25% (real robot) outperforming SOTA methods.

cs.RO↗

arXiv2025

TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation

Video generation models are revolutionizing content creation, with image-to-video models drawing increasing attention due to their enhanced controllability, visual consistency, and practical applications. However, despite their popularity, these models rely on user-provided text and image prompts, and there is currently no dedicated dataset for studying these prompts. In this paper, we introduce TIP-I2V, the first large-scale dataset of over 1.70 million unique user-provided Text and Image Prompts specifically for Image-to-Video generation. Additionally, we provide the corresponding generated videos from five state-of-the-art image-to-video models. We begin by outlining the time-consuming and costly process of curating this large-scale dataset. Next, we compare TIP-I2V to two popular prompt datasets, VidProM (text-to-video) and DiffusionDB (text-to-image), highlighting differences in both basic and semantic information. This dataset enables advancements in image-to-video research. For instance, to develop better models, researchers can use the prompts in TIP-I2V to analyze user preferences and evaluate the multi-dimensional performance of their trained models; and to enhance model safety, they may focus on addressing the misinformation issue caused by image-to-video models. The new research inspired by TIP-I2V and the differences with existing datasets emphasize the importance of a specialized image-to-video prompt dataset. The project is available at https://tip-i2v.github.io.

cs.CV↗

arXiv2025

Scaling 4D Representations

Scaling has not yet been convincingly demonstrated for pure self-supervised learning from video. However, prior work has focused evaluations on semantic-related tasks $\unicode{x2013}$ action classification, ImageNet classification, etc. In this paper we focus on evaluating self-supervised learning on non-semantic vision tasks that are more spatial (3D) and temporal (+1D = 4D), such as camera pose estimation, point and object tracking, and depth estimation. We show that by learning from very large video datasets, masked auto-encoding (MAE) with transformer video models actually scales, consistently improving performance on these 4D tasks, as model size increases from 20M all the way to the largest by far reported self-supervised video model $\unicode{x2013}$ 22B parameters. Rigorous apples-to-apples comparison with many recent image and video models demonstrates the benefits of scaling 4D representations. Pretrained models are available at https://github.com/google-deepmind/representations4d .

cs.CV↗

arXiv2025

Parity-time symmetry phase transition in photonic time-modulated media

Time modulation can cause gain and loss in photonic media, leading to complex modal behaviors and enhanced wave controllability in the non-Hermitian regime. Conversely, we reveal that Hermiticity and parity-time $\mathcal{PT}$-symmetry phase transition are possible under the temporal $\mathcal{PT}$-symmetry in time-modulated photonic media. We prove that, for a homogeneously modulated photonic medium with complex-valued modulation, temporal $\mathcal{PT}$-symmetry is a necessary but insufficient condition for obtaining a real eigenvalue spectrum, giving rise to $\mathcal{PT}$-symmetry phase transition. Specifically, the $\mathcal{PT}$ phase transition critically depends on the contrast between the modulation depth of the real and imaginary parts of permittivity when they are sinusoidally modulated with a $π/2$ phase difference. We generalize the discretized temporal-interface transfer matrix method to a continuous differential operator framework, which facilitates the confirmation of the phase transition condition via Magnus expansion analysis. Full-wave simulations and analytical calculations jointly confirm the occurrence of $\mathcal{PT}$-transition by examining the scattering behavior of a propagating pulse in such a type of modulated medium. The findings provide a temporal $\mathcal{PT}$-symmetric paradigm for controlling Hermiticity and non-Hermiticity in spatiotemporal photonic systems.

physics.optics↗

arXiv2025

UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis

Text-to-image generation has greatly advanced content creation, yet accurately rendering visual text remains a key challenge due to blurred glyphs, semantic drift, and limited style control. Existing methods often rely on pre-rendered glyph images as conditions, but these struggle to retain original font styles and color cues, necessitating complex multi-branch designs that increase model overhead and reduce flexibility. To address these issues, we propose a segmentation-guided framework that uses pixel-level visual text masks -- rich in glyph shape, color, and spatial detail -- as unified conditional inputs. Our method introduces two core components: (1) a fine-tuned bilingual segmentation model for precise text mask extraction, and (2) a streamlined diffusion model augmented with adaptive glyph conditioning and a region-specific loss to preserve textual fidelity in both content and style. Our approach achieves state-of-the-art performance on the AnyText benchmark, significantly surpassing prior methods in both Chinese and English settings. To enable more rigorous evaluation, we also introduce two new benchmarks: GlyphMM-benchmark for testing layout and glyph consistency in complex typesetting, and MiniText-benchmark for assessing generation quality in small-scale text regions. Experimental results show that our model outperforms existing methods by a large margin in both scenarios, particularly excelling at small text rendering and complex layout preservation, validating its strong generalization and deployment readiness.

cs.CV↗

arXiv2025

Achieving binary weight and activation for LLMs using Post-Training Quantization

Quantizing large language models (LLMs) to 1-bit precision significantly reduces computational costs, but existing quantization techniques suffer from noticeable performance degradation when using weight and activation precisions below 4 bits (W4A4). In this paper, we propose a post-training quantization framework with W(1+1)A(1*4) configuration, where weights are quantized to 1 bit with an additional 1 bit for fine-grain grouping and activations are quantized to 1 bit with a 4-fold increase in the number of channels. For weight quantization, we propose utilizing Hessian-aware fine-grained grouping along with an EM-based quantization scheme. For activation quantization, we decompose INT4-quantized activations into a 4 * INT1 format equivalently and simultaneously smooth the scaling factors based on quantization errors, which further reduces the quantization errors in activations. Our method surpasses state-of-the-art (SOTA) LLM quantization baselines on W2A4 across multiple tasks, pushing the boundaries of existing LLM quantization methods toward fully binarized models. Code is available at https://github.com/JimmyCrave/LLM-PTQ-binarization.

cs.LG↗

arXiv2025

FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion

Recent advances in video generation models have enabled high-quality short video generation from text prompts. However, extending these models to longer videos remains a significant challenge, primarily due to degraded temporal consistency and visual fidelity. Our preliminary observations show that naively applying short-video generation models to longer sequences leads to noticeable quality degradation. Further analysis identifies a systematic trend where high-frequency components become increasingly distorted as video length grows, an issue we term high-frequency distortion. To address this, we propose FreeLong, a training-free framework designed to balance the frequency distribution of long video features during the denoising process. FreeLong achieves this by blending global low-frequency features, which capture holistic semantics across the full video, with local high-frequency features extracted from short temporal windows to preserve fine details. Building on this, FreeLong++ extends FreeLong dual-branch design into a multi-branch architecture with multiple attention branches, each operating at a distinct temporal scale. By arranging multiple window sizes from global to local, FreeLong++ enables multi-band frequency fusion from low to high frequencies, ensuring both semantic continuity and fine-grained motion dynamics across longer video sequences. Without any additional training, FreeLong++ can be plugged into existing video generation models (e.g. Wan2.1 and LTX-Video) to produce longer videos with substantially improved temporal consistency and visual fidelity. We demonstrate that our approach outperforms previous methods on longer video generation tasks (e.g. 4x and 8x of native length). It also supports coherent multi-prompt video generation with smooth scene transitions and enables controllable video generation using long depth or pose sequences.

cs.CV↗

arXiv2025

TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models

Reliable semantic segmentation of open environments is essential for intelligent systems, yet significant problems remain: 1) Existing RGB-T semantic segmentation models mainly rely on low-level visual features and lack high-level textual information, which struggle with accurate segmentation when categories share similar visual characteristics. 2) While SAM excels in instance-level segmentation, integrating it with thermal images and text is hindered by modality heterogeneity and computational inefficiency. To address these, we propose TASeg, a text-aware RGB-T segmentation framework by using Low-Rank Adaptation (LoRA) fine-tuning technology to adapt vision foundation models. Specifically, we propose a Dynamic Feature Fusion Module (DFFM) in the image encoder, which effectively merges features from multiple visual modalities while freezing SAM's original transformer blocks. Additionally, we incorporate CLIP-generated text embeddings in the mask decoder to enable semantic alignment, which further rectifies the classification error and improves the semantic understanding accuracy. Experimental results across diverse datasets demonstrate that our method achieves superior performance in challenging scenarios with fewer trainable parameters.

cs.CV↗

arXiv2025

Chemical knowledge-informed framework for privacy-aware retrosynthesis learning

Chemical reaction data is a pivotal asset, driving advances in competitive fields such as pharmaceuticals, materials science, and industrial chemistry. Its proprietary nature renders it sensitive, as it often includes confidential insights and competitive advantages organizations strive to protect. However, in contrast to this need for confidentiality, the current standard training paradigm for machine learning-based retrosynthesis gathers reaction data from multiple sources into one single edge to train prediction models. This paradigm poses considerable privacy risks as it necessitates broad data availability across organizational boundaries and frequent data transmission between entities, potentially exposing proprietary information to unauthorized access or interception during storage and transfer. In the present study, we introduce the chemical knowledge-informed framework (CKIF), a privacy-preserving approach for learning retrosynthesis models. CKIF enables distributed training across multiple chemical organizations without compromising the confidentiality of proprietary reaction data. Instead of gathering raw reaction data, CKIF learns retrosynthesis models through iterative, chemical knowledge-informed aggregation of model parameters. In particular, the chemical properties of predicted reactants are leveraged to quantitatively assess the observable behaviors of individual models, which in turn determines the adaptive weights used for model aggregation. On a variety of reaction datasets, CKIF outperforms several strong baselines by a clear margin.

cs.LG↗

arXiv2025

Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space

Recent advances in operator learning have produced two distinct approaches for solving partial differential equations (PDEs): attention-based methods offering point-level adaptability but lacking spectral constraints, and spectral-based methods providing domain-level continuity priors but limited in local flexibility. This dichotomy has hindered the development of PDE solvers with both strong flexibility and generalization capability. This work introduces Holistic Physics Mixer (HPM), a simple framework that bridges this gap by integrating spectral and physical information in a unified space. HPM unifies both approaches as special cases while enabling more powerful spectral-physical interactions beyond either method alone. This enables HPM to inherit both the strong generalization of spectral methods and the flexibility of attention mechanisms while avoiding their respective limitations. Through extensive experiments across diverse PDE problems, we demonstrate that HPM consistently outperforms state-of-the-art methods in both accuracy and computational efficiency, while maintaining strong generalization capabilities with limited training data and excellent zero-shot performance on unseen resolutions.

cs.LG↗

arXiv2025

MCOO-SLAM: A Multi-Camera Omnidirectional Object SLAM System

Object-level SLAM offers structured and semantically meaningful environment representations, making it more interpretable and suitable for high-level robotic tasks. However, most existing approaches rely on RGB-D sensors or monocular views, which suffer from narrow fields of view, occlusion sensitivity, and limited depth perception-especially in large-scale or outdoor environments. These limitations often restrict the system to observing only partial views of objects from limited perspectives, leading to inaccurate object modeling and unreliable data association. In this work, we propose MCOO-SLAM, a novel Multi-Camera Omnidirectional Object SLAM system that fully leverages surround-view camera configurations to achieve robust, consistent, and semantically enriched mapping in complex outdoor scenarios. Our approach integrates point features and object-level landmarks enhanced with open-vocabulary semantics. A semantic-geometric-temporal fusion strategy is introduced for robust object association across multiple views, leading to improved consistency and accurate object modeling, and an omnidirectional loop closure module is designed to enable viewpoint-invariant place recognition using scene-level descriptors. Furthermore, the constructed map is abstracted into a hierarchical 3D scene graph to support downstream reasoning tasks. Extensive experiments in real-world demonstrate that MCOO-SLAM achieves accurate localization and scalable object-level mapping with improved robustness to occlusion, pose variation, and environmental complexity.

cs.RO↗

arXiv2025

Average-case deterministic query complexity of boolean functions with fixed weight

We study the $\textit{average-case deterministic query complexity}$ of boolean functions under a $\textit{uniform input distribution}$, denoted by $\mathrm{D}_\mathrm{ave}(f)$, the minimum average depth of zero-error decision trees that compute a boolean function $f$. This measure has found several applications across diverse fields, yet its understanding is limited. We study boolean functions with fixed weight, where weight is defined as the number of inputs on which the output is $1$. We prove $\mathrm{D}_\mathrm{ave}(f) \le \max \left\{ \log \frac{\mathrm{wt}(f)}{\log n} + O(\log \log \frac{\mathrm{wt}(f)}{\log n}), O(1) \right\}$ for every $n$-variable boolean function $f$, where $\mathrm{wt}(f)$ denotes the weight. For any $4\log n \le m(n) \le 2^{n-1}$, we prove the upper bound is tight up to an additive logarithmic term for almost all $n$-variable boolean functions with fixed weight $\mathrm{wt}(f) = m(n)$. Håstad's switching lemma or Rossman's switching lemma [Comput. Complexity Conf. 137, 2019] implies $\mathrm{D}_\mathrm{ave}(f) \leq n\left(1 - \frac{1}{O(w)}\right)$ or $\mathrm{D}_\mathrm{ave}(f) \le n\left(1 - \frac{1}{O(\log s)}\right)$ for CNF/DNF formulas of width $w$ or size $s$, respectively. We show there exists a DNF formula of width $w$ and size $\lceil 2^w / w \rceil$ such that $\mathrm{D}_\mathrm{ave}(f) = n \left(1 - \frac{\log n}{Θ(w)}\right)$ for any $w \ge 2\log n$.

cs.CC↗

arXiv2025

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering

High-quality novel view synthesis for large-scale scenes presents a challenging dilemma in 3D computer vision. Existing methods typically partition large scenes into multiple regions, reconstruct a 3D representation using Gaussian splatting for each region, and eventually merge them for novel view rendering. They can accurately render specific scenes, yet they do not generalize effectively for two reasons: (1) rigid spatial partition techniques struggle with arbitrary camera trajectories, and (2) the merging of regions results in Gaussian overlap to distort texture details. To address these challenges, we propose TraGraph-GS, leveraging a trajectory graph to enable high-precision rendering for arbitrarily large-scale scenes. We present a spatial partitioning method for large-scale scenes based on graphs, which incorporates a regularization constraint to enhance the rendering of textures and distant objects, as well as a progressive rendering strategy to mitigate artifacts caused by Gaussian overlap. Experimental results demonstrate its superior performance both on four aerial and four ground datasets and highlight its remarkable efficiency: our method achieves an average improvement of 1.86 dB in PSNR on aerial datasets and 1.62 dB on ground datasets compared to state-of-the-art approaches.

cs.CV↗

arXiv2025

A post-common-envelope binary with double-peaked Balmer emission lines from TMTS

The dynamical method provides an efficient way to discover post-common-envelope binaries (PCEB) with faint white dwarfs (WDs), thanks to the development of time-domain survey projects. We perform a comprehensive analysis of the PCEB system TMTS J15530469+4457458 (J1553), discovered by the Tsinghua University-Ma Huateng Telescopes for Survey, to explore its physical origin and evolutionary fate. This system is characterized by double-peaked Balmer emission lines, and a cross-correlation function is applied to derive its radial velocity (RV) from a series of phase-resolved Keck spectra. Analyses with the cross-correlation function suggest that this system is a single-lined spectroscopic binary and only one star is optically visible. Further analysis through Doppler tomography indicates that J1553 is a detached binary without an accretion disk. Under such a configuration, the simultaneous light-curve and RV fitting reveal that this system contains an unseen WD with mass $M_{\rm A}=0.56\pm 0.09\, M_{\odot}$, and an M4 dwarf with mass $M_{\rm B}=0.37\pm 0.02\,M_{\odot}$ and radius $R_{\rm B}=0.403^{+0.014}_{-0.015}\,R_{\odot}$. The extra prominent Balmer emission lines seen in the spectra can trace the motion of the WD, which are likely formed near the WD surface as a result of wind accretion. According to the MESA simulation, J1553 could have evolved from a binary consisting of a 2.0-4.0 ${M}_{\odot}$ zero-age-main-sequence star and an M dwarf with an initial orbital period $P_i\approx 201-476$ d, and the system has undergone a common-envelope (CE) phase. After about $3.3\times10^6$ yr, J1553 should evolve into a cataclysmic variable, with a transient state as a supersoft X-ray source at the beginning. J1553 is an excellent system for studying wind accretion, CE ejection physics, and binary evolution theory.

astro-ph.SR↗

arXiv2025

Object Navigation with Structure-Semantic Reasoning-Based Multi-level Map and Multimodal Decision-Making LLM

The zero-shot object navigation (ZSON) in unknown open-ended environments coupled with semantically novel target often suffers from the significant decline in performance due to the neglect of high-dimensional implicit scene information and the long-range target searching task. To address this, we proposed an active object navigation framework with Environmental Attributes Map (EAM) and MLLM Hierarchical Reasoning module (MHR) to improve its success rate and efficiency. EAM is constructed by reasoning observed environments with SBERT and predicting unobserved ones with Diffusion, utilizing human space regularities that underlie object-room correlations and area adjacencies. MHR is inspired by EAM to perform frontier exploration decision-making, avoiding the circuitous trajectories in long-range scenarios to improve path efficiency. Experimental results demonstrate that the EAM module achieves 64.5\% scene mapping accuracy on MP3D dataset, while the navigation task attains SPLs of 28.4\% and 26.3\% on HM3D and MP3D benchmarks respectively - representing absolute improvements of 21.4\% and 46.0\% over baseline methods.

cs.RO↗

arXiv2025

EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space

Diffusion models, particularly latent diffusion models, have demonstrated remarkable success in text-driven human motion generation. However, it remains challenging for latent diffusion models to effectively compose multiple semantic concepts into a single, coherent motion sequence. To address this issue, we propose EnergyMoGen, which includes two spectrums of Energy-Based Models: (1) We interpret the diffusion model as a latent-aware energy-based model that generates motions by composing a set of diffusion models in latent space; (2) We introduce a semantic-aware energy model based on cross-attention, which enables semantic composition and adaptive gradient descent for text embeddings. To overcome the challenges of semantic inconsistency and motion distortion across these two spectrums, we introduce Synergistic Energy Fusion. This design allows the motion latent diffusion model to synthesize high-quality, complex motions by combining multiple energy terms corresponding to textual descriptions. Experiments show that our approach outperforms existing state-of-the-art models on various motion generation tasks, including text-to-motion generation, compositional motion generation, and multi-concept motion generation. Additionally, we demonstrate that our method can be used to extend motion datasets and improve the text-to-motion task.

cs.CV↗

arXiv2025

Large Cold Dust Reservoir Revealed in Transitional SN Ib 2014C by James Webb Space Telescope Mid-Infrared Spectroscopy

Supernova (SN) 2014C is a rare transitional event that exploded as a hydrogen-poor, helium-rich Type Ib SN and subsequently interacted with a hydrogen-rich circumstellar medium (CSM) a few months post-explosion. This unique interacting object provides an opportunity to probe the mass-loss history of a stripped-envelope SN progenitor. Using the James Webb Space Telescope (JWST), we observed SN 2014C with the Mid-Infrared Instrument Medium Resolution Spectrometer at 3477 days post-explosion (rest frame), and the Near-Infrared Spectrograph Integral Field Unit at 3568 days post-explosion, covering 1.7 to 25 $μ$m. The bolometric luminosity indicates that the SN is still interacting with the same CSM that was observed with the Spitzer Space Telescope 40--1920 days post-explosion. JWST spectra and near-contemporaneous optical and near-infrared spectra show strong [Ne II] 12.831 $μ$m, He 1.083 $μ$m, H$α$, and forbidden oxygen ([O I] $λ$$λ$6300, 6364, [O II] $λ$$λ$7319, 7330, and [O III] $λ$$λ$4959, 5007) emission lines with asymmetric profiles, suggesting a highly asymmetric CSM. The mid-IR continuum can be explained by ~$0.036 \ M_\odot$ of carbonaceous dust at ~300 K and ~0.043 $M_\odot$ of silicate dust at ~200 K. The observed dust mass has increased tenfold since the last Spitzer observation 4 yr ago, with evidence suggesting that new grains have condensed in the cold dense shell between the forward and reverse shocks. This dust mass places SN 2014C among the dustiest SNe in the mid-IR and supports the emerging observational trend that SN explosions produce enough dust to explain the observed dust mass at high redshifts.

astro-ph.HE↗

arXiv2025

Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generation

Advances in talking-head animation based on Latent Diffusion Models (LDM) enable the creation of highly realistic, synchronized videos. These fabricated videos are indistinguishable from real ones, increasing the risk of potential misuse for scams, political manipulation, and misinformation. Hence, addressing these ethical concerns has become a pressing issue in AI security. Recent proactive defense studies focused on countering LDM-based models by adding perturbations to portraits. However, these methods are ineffective at protecting reference portraits from advanced image-to-video animation. The limitations are twofold: 1) they fail to prevent images from being manipulated by audio signals, and 2) diffusion-based purification techniques can effectively eliminate protective perturbations. To address these challenges, we propose Silencer, a two-stage method designed to proactively protect the privacy of portraits. First, a nullifying loss is proposed to ignore audio control in talking-head generation. Second, we apply anti-purification loss in LDM to optimize the inverted latent feature to generate robust perturbations. Extensive experiments demonstrate the effectiveness of Silencer in proactively protecting portrait privacy. We hope this work will raise awareness among the AI security community regarding critical ethical issues related to talking-head generation techniques. Code: https://github.com/yuangan/Silencer.

cs.GR↗