arXiv subjects

Tong Lin

Publications and source records attributed to Tong Lin.

At least 19 recordsLinked to original sources

arXiv2026

DLAM: Distributional Latent Actions with Temporal Constraints

Vision-language-action (VLA) models remain constrained by scarce action-labeled robot data, whereas action-free videos offer abundant observations of physical change. Latent action models can extract such priors, but reconstruction-trained codes may predict future observations without the structure required for joint generation with robot actions. Existing structured methods add temporal constraints but retain deterministic transition points, so residual errors in locally inferred transitions may propagate and compound under recursive composition. We introduce DLAM, a distributional latent-action model that represents each transition as a diagonal Gaussian. Reconstruction conditioned on the reference frame grounds the mean in observed visual change, while normalized composition and reversal over equal-gap triplets constrain both the mean and dimension-wise variance. Variance composition uses a lightweight shared-correlation coefficient to account for dependence between adjacent transitions that share an intermediate frame, whereas reversal negates the mean and preserves the variance. For downstream policy learning, we freeze the encoder and train a flow-matching policy to jointly generate mean transition sequences and robot actions. On held-out transitions, DLAM learns more temporally consistent latent dynamics than existing latent-action baselines and achieves stronger direct and cumulative reconstruction on held-out videos. Under the same controlled $\pi_0$ transfer protocol, it also improves policy performance on MetaWorld MT50, LIBERO, and real-world manipulation tasks. Controlled ablations show that normalized mean constraints account for most of the reconstruction gain, while learned variance and correlation-aware composition provide complementary improvements in downstream control.

cs.RO↗

arXiv2026

Non-Hermitian topology driven by an identity term: An exactly solvable paradigm

An identity term in the Hamiltonian is conventionally regarded as spectrally inert-it shifts energies but does not alter eigenstate topology. We show that under non-Hermitian skin pumping, this paradigm fails: a momentum-dependent identity term actively deforms the generalized Brillouin zone, thereby challenging established topological criteria that rely on fixed complex contours. Here, by introducing spin-orbit coupling into a Hatano-Nelson chain, we present an exact analytical solution for the entire non-Hermitian eigensystem under open boundary conditions. Our solution reveals how inter-cell spin-orbit coupling, synergizing with this non-trivial identity term, induces topological edge states and robust zero modes in the complete absence of chiral symmetry. This work establishes an exactly solvable paradigm for non-Hermitian topology beyond symmetry protection, and provides a rigorous benchmark for testing topological invariants in systems with momentum-dependent identity terms.

quant-ph↗

arXiv2026

ABot-M0.5: Unified Mobility-and-Manipulation World Action Model

Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typically reactive and lack explicit world modeling, while existing World Action Models (WAMs) are still poorly aligned with the structure of mobile manipulation: they operate on coarse video chunks, model entangled navigation-manipulation actions, and train inverse dynamics under supervision that does not match autoregressive inference. As a result, they often miss fine-grained contact dynamics, suffer from action-distribution conflicts, and accumulate errors over long-horizon rollouts. We propose ABot-M0.5, a new WAM built on the insight that mobile manipulation requires alignment at three levels: temporal granularity, action space, and train-test consistency. To align temporal granularity, we introduce intermediate latent actions that capture local visual state transitions and serve as an bridging action space between video latents and embodiment-specific controls. To align action space, we design a dual-level Mixture-of-Transformers architecture that disentangles both modality representations and heterogeneous action subspaces such as base movement and arm manipulation. To align inference conditions, we propose the dream-forcing training strategy that progressively trains inverse dynamics on model-predicted videos, improving train-test alignment and robustness during autoregressive prediction. Experiments on challenging mobile and fine-grained manipulation benchmarks demonstrate that ABot-M0.5 achieves state-of-the-art performance in both long-horizon task success and finegrained control accuracy. These results highlight the critical importance of granularity-aligned, action-disentangled, and inference-consistent world-action modeling.

cs.CV↗

arXiv2026

What to Format and How: A Benchmark and Workflow Approach for Document Formatting

Recent advances in large language models (LLMs) have opened up new possibilities for automated document formatting. However, real-world formatting often requires identifying targets based on document content. This content-aware setting remains challenging and underexplored, primarily due to the lack of dedicated evaluation datasets.To enable evaluation in realistic content-aware scenarios, we introduce DocFormBench, a benchmark that extends Text-to-Format evaluation to diverse formatting requirements, along with metrics for both accuracy and efficiency.To mitigate redundant document reading in existing methods during formatting, we propose DocFormFlow, a workflow formatting method that decouples target localization from modification execution into what to format and how. Extensive experiments across multiple LLMs and multimodal models show that DocFormFlow consistently improves formatting accuracy while reducing token consumption compared to representative baselines. Further analysis reveals that precise target localization is the primary factor influencing formatting performance. We hope DocFormBench and DocFormFlow will facilitate future research toward more intelligent and reliable document formatting.

cs.CL↗

arXiv2026

Model-free estimation in scattering analysis of microscopy

The mean squared displacement (MSD) of particles or probes is commonly estimated from microscopy videos using particle tracking approaches, which rely on tuning parameters manually, and are often unstable over the entire lag time range, especially in dense or low-contrast situations. In this work, we propose model-free ab initio uncertainty quantification (MF-AIUQ), a model-free method for scattering analysis of microscopy video based on a probabilistic framework, which estimates MSD without isolating particles and linking their trajectories. Based on the relationship between the intermediate scattering function (ISF) and the MSD derived from the cumulant theorem, MF-AIUQ estimates the MSD values by the marginal maximum likelihood estimator. To reduce the computational cost, the likelihood function is approximated by a subset of Fourier-transformed intensities. These intensities are equally spaced at the logarithmic values of Fourier basis functions and lag time points. We found that the ISF is smooth in this logarithmic input space, and the information of the ISF can be captured by this subset of inputs. We examine the method through simulation studies covering several representative stochastic processes and three experimental systems: a Newtonian fluid for evaluating performance in optically dense and bright-field settings, a gelation system with an evolving MSD shape, and snail mucin, a viscoelastic biopolymer, for modulus estimation. Across these studies, MF-AIUQ provides smooth and stable MSD estimates over the full lag time range and serves as a useful complementary approach in settings where particle tracking is unreliable or a parametric model of MSD is unavailable or unverifiable.

stat.AP↗

arXiv2026

Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation

This paper tackles spatial perception and manipulation challenges in Vision-Language-Action (VLA) models. To address depth ambiguity from monocular input, we leverage a pre-trained multi-view diffusion model to synthesize latent novel views and propose a Geometry-Guided Gated Transformer (G3T) that aligns multi-view features under 3D geometric guidance while adaptively filtering occlusion noise. To improve action learning efficiency, we introduce Action Manifold Learning (AML), which directly predicts actions on the valid action manifold, bypassing inefficient regression of unstructured targets like noise or velocity. Experiments on LIBERO, RoboTwin 2.0, and real-robot tasks show our method achieves superior success rate and robustness over SOTA baselines. Project page: https://junjxiao.github.io/Multi-view-VLA.github.io/.

cs.RO↗

arXiv2026

Accessible pore geometry governs tracer diffusion in crowded environments

Tracer diffusion in crowded environments is central to many biological and soft matter systems, but quantitative frameworks for linking tracer motion to environmental structure remain limited, and the co-dependence among geometric variables that facilitate or hinder tracer transport is not yet well understood. Here, we study the transport of rigid tracers in suspensions of soft particles and within living cells. Experiments reveal a transition from diffusive to confined motion as the matrix area fraction increases. The observed ensemble-level statistics, including the mean-squared displacements (MSDs), can be reproduced using a minimal simulation. Using simulation outputs, we train a parallel partial Gaussian process (PPGP) model that rapidly predicts MSDs from matrix geometric variables, including area fraction, particle size, and polydispersity. Analysis reveals that tracer transport is primarily governed by accessible pore sizes and that distinct global structures can produce indistinguishable MSDs. While MSDs do not uniquely encode system geometrical parameters, we nevertheless find correspondence between pore size distribution and the ensemble MSDs. By modeling matrix self-diffusivity, the minimal model can also phenomenologically describe MSDs of internalized tracer particles in cells. The framework enables rapid inference of structural properties in crowded environments, including transport in the intracellular environment.

cond-mat.soft↗

arXiv2026

Long-Text-to-Image Generation via Compositional Prompt Decomposition

While modern text-to-image (T2I) models excel at generating images from intricate prompts, they struggle to capture the key details when the inputs are descriptive paragraphs. This limitation stems from the prevalence of concise captions that shape their training distributions. Existing methods attempt to bridge this gap by either fine-tuning T2I models on long prompts, which generalizes poorly to longer lengths; or by projecting the oversize inputs into normal-prompt space and compromising fidelity. We propose Prompt Refraction for Intricate Scene Modeling (PRISM), a compositional approach that enables pre-trained T2I models to process long sequence inputs. PRISM uses a lightweight module to extract constituent representations from the long prompts. The T2I model makes independent noise predictions for each component, and their outputs are merged into a single denoising step using energy-based conjunction. We evaluate PRISM across a wide range of model architectures, showing comparable performances to models fine-tuned on the same training data. Furthermore, PRISM demonstrates superior generalization, outperforming baseline models by 7.4% on prompts over 500 tokens in a challenging public benchmark.

cs.CV↗

arXiv2026

ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment

Video-based world models offer a powerful paradigm for embodied simulation and planning, yet state-of-the-art models often generate physically implausible manipulations - such as object penetration and anti-gravity motion - due to training on generic visual data and likelihood-based objectives that ignore physical laws. We present ABot-PhysWorld, a 14B Diffusion Transformer model that generates visually realistic, physically plausible, and action-controllable videos. Built on a curated dataset of three million manipulation clips with physics-aware annotation, it uses a novel DPO-based post-training framework with decoupled discriminators to suppress unphysical behaviors while preserving visual quality. A parallel context block enables precise spatial action injection for cross-embodiment control. To better evaluate generalization, we introduce EZSbench, the first training-independent embodied zero-shot benchmark combining real and synthetic unseen robot-task-scene combinations. It employs a decoupled protocol to separately assess physical realism and action alignment. ABot-PhysWorld achieves new state-of-the-art performance on PBench and EZSbench, surpassing Veo 3.1 and Sora v2 Pro in physical plausibility and trajectory consistency. We will release EZSbench to promote standardized evaluation in embodied video generation.

cs.CV↗

arXiv2026

Exceptional Optical Phonon Coherence in Enriched Cubic Boron Arsenide via Suppression of Three-Phonon Scattering

Cubic boron arsenide (BAs) is a promising semiconductor for next-generation electronics due to its outstanding ambipolar mobility and thermal conductivity, the latter of which is attributed to the suppression of three-phonon scattering. However, precisely accounting for different high-order anharmonic scattering processes is challenging from both theory and experiment, so that questions remain open regarding the ultimate limit of phonon lifetime and thermal conductivity in BAs. Here we show that this gap nearly eliminates three-phonon scattering for zone-center optical phonons in a wide temperature range, leading to a record-high, isotope purity-limited phonon coherence with a quality factor above $3.7\times 10^3$ for >98% enriched $^{11}$BAs below 100 K. We discriminate three decoherence mechanisms by their temperature-dependent contribution to the damping rate using high-resolution Raman and Fourier transform infrared spectroscopy. For the as-synthesized crystals, we find that defect scattering has negligible contributions to the linewidth of optical phonons in comparison to isotope scattering. These results provide critical insights into the intrinsic and extrinsic scattering mechanisms of optical phonons in BAs, motivating further studies to quantify anharmonic effects and realize superior phonon transport.

cond-mat.mtrl-sci↗

arXiv2026

Neural Implicit Action Fields: From Discrete Waypoints to Continuous Functions for Vision-Language-Action Models

Despite the rapid progress of vision-language-action (VLA) models, the prevailing practice of predicting action chunks as discrete waypoints remains structurally misaligned with the intrinsic continuity of physical motion. This discretization arises naturally from fixed-rate robot data collection and the token-by-token prediction paradigm of large language models, but ties actions to rigid sampling rates, does not naturally support analytically consistent higher-order derivatives, and introduces quantization artifacts that hinder precise, compliant interaction. We propose Neural Implicit Action Fields (NIAF), which reformulates chunk-level action representation from discrete waypoints to continuous action functions. Using a vision-language model as a hierarchical spectral modulator over a learnable motion prior, NIAF synthesizes continuous-time action manifolds with arbitrary temporal resolution. This formulation enables analytical differentiation, allowing explicit supervision of velocity and regularization of higher-order derivative signals to promote mathematical consistency, physical plausibility, and control smoothness. Our approach achieves strong results on CALVIN and LIBERO across diverse backbones. Real-world experiments further confirm that NIAF supports stable impedance control, bridging policy-side action generation and execution-side smooth control.

cs.RO↗

arXiv2026

ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning

Building general-purpose embodied agents across diverse hardware remains a central challenge in robotics, often framed as the ''one-brain, many-forms'' paradigm. Progress is hindered by fragmented data, inconsistent representations, and misaligned training objectives. We present ABot-M0, a framework that builds a systematic data curation pipeline while jointly optimizing model architecture and training strategies, enabling end-to-end transformation of heterogeneous raw data into unified, efficient representations. From six public datasets, we clean, standardize, and balance samples to construct UniACT-dataset, a large-scale dataset with over 6 million trajectories and 9,500 hours of data, covering diverse robot morphologies and task scenarios. Unified pre-training improves knowledge transfer and generalization across platforms and tasks, supporting general-purpose embodied intelligence. To improve action prediction efficiency and stability, we propose the Action Manifold Hypothesis: effective robot actions lie not in the full high-dimensional space but on a low-dimensional, smooth manifold governed by physical laws and task constraints. Based on this, we introduce Action Manifold Learning (AML), which uses a DiT backbone to predict clean, continuous action sequences directly. This shifts learning from denoising to projection onto feasible manifolds, improving decoding speed and policy stability. ABot-M0 supports modular perception via a dual-stream mechanism that integrates VLM semantics with geometric priors and multi-view inputs from plug-and-play 3D modules such as VGGT and Qwen-Image-Edit, enhancing spatial understanding without modifying the backbone and mitigating standard VLM limitations in 3D reasoning. Experiments show components operate independently with additive benefits. We will release all code and pipelines for reproducibility and future research.

cs.CV↗

arXiv2026

FARTrack: Fast Autoregressive Visual Tracking with High Performance

Inference speed and tracking performance are two critical evaluation metrics in the field of visual tracking. However, high-performance trackers often suffer from slow processing speeds, making them impractical for deployment on resource-constrained devices. To alleviate this issue, we propose FARTrack, a Fast Auto-Regressive Tracking framework. Since autoregression emphasizes the temporal nature of the trajectory sequence, it can maintain high performance while achieving efficient execution across various devices. FARTrack introduces Task-Specific Self-Distillation and Inter-frame Autoregressive Sparsification, designed from the perspectives of shallow-yet-accurate distillation and redundant-to-essential token optimization, respectively. Task-Specific Self-Distillation achieves model compression by distilling task-specific tokens layer by layer, enhancing the model's inference speed while avoiding suboptimal manual teacher-student layer pairs assignments. Meanwhile, Inter-frame Autoregressive Sparsification sequentially condenses multiple templates, avoiding additional runtime overhead while learning a temporally-global optimal sparsification strategy. FARTrack demonstrates outstanding speed and competitive performance. It delivers an AO of 70.6% on GOT-10k in real-time. Beyond, our fastest model achieves a speed of 343 FPS on the GPU and 121 FPS on the CPU.

cs.CV↗

arXiv2025

GeoPep: A geometry-aware masked language model for protein-peptide binding site prediction

Multimodal approaches that integrate protein structure and sequence have achieved remarkable success in protein-protein interface prediction. However, extending these methods to protein-peptide interactions remains challenging due to the inherent conformational flexibility of peptides and the limited availability of structural data that hinder direct training of structure-aware models. To address these limitations, we introduce GeoPep, a novel framework for peptide binding site prediction that leverages transfer learning from ESM3, a multimodal protein foundation model. GeoPep fine-tunes ESM3's rich pre-learned representations from protein-protein binding to address the limited availability of protein-peptide binding data. The fine-tuned model is further integrated with a parameter-efficient neural network architecture capable of learning complex patterns from sparse data. Furthermore, the model is trained using distance-based loss functions that exploit 3D structural information to enhance binding site prediction. Comprehensive evaluations demonstrate that GeoPep significantly outperforms existing methods in protein-peptide binding site prediction by effectively capturing sparse and heterogeneous binding patterns.

eess.SP↗

arXiv2025

Ultracompact high-Q whispering gallery mode microresonator in a non-closed waveguide path

Integrated photonic circuits are foundational for versatile applications, where high-performance traveling-wave optical resonators are critical. Conventional whispering-gallery mode microresonators (WGMRs) confine light in closed-loop waveguide paths, thus inevitably occupy large footprints. Here, we report an ultracompact high loaded Q silicon photonic WGMR in an open curved path instead. By leveraging spatial mode multiplexing, low-loss mode converter-based photonic routers enable reentrant photon recycling in a single non-closed waveguide. The fabricated device achieves a measured loaded Q-factor of 1.78*10^5 at 1554.3 nm with a 1.05 nm free spectral range in a ultracompact footprint of 0.00137 mm^2-6*smaller than standard WGMRs while delivering 100*higher Q-factor than photonic crystal counterparts. This work pioneers dense integration of high-performance WGMR arrays through open-path mode recirculation.

physics.optics↗

arXiv2025

Integrated Silicon Photonic Multichannel Optical Hybrid for Broadband Parallel Coherent Reception

We design and demonstrate a monolithically integrated silicon photonic multichannel optical hybrid for versatile broadband coherent reception, addressing the critical limitations of current wavelength multiplexed systems in scalability and power efficiency. The device combines a phase-compensated 90-degree optical hybrid with four robust three-stage Mach-Zehnder interferometer lattice filters, enabling 34-port functionality (two inputs and 32 outputs) for simultaneous analog and digital signal processing. Leveraging multimode interferometer designs,the chip achieves a broadband response with sub-dB passband uniformity across eight 200 GHz-spaced wavelength channels, while maintaining phase errors below 4 degrees over a 13.5 nm (1539-1552.5 nm) bandwidth with only 2.5 mW thermal tuning power.Experimentally, we validate its parallel-processing capability through RF channelizer reception (showing an average spurious-free dynamic range of 80.8 dB*Hz2/3 and image rejection ratio of 33.26 dB) and coherent optical communication (achieving 1.024 Tb/s data rate for 32-QAM signals with bit error rates far below the 20% SD-FEC threshold). The scheme enhances system performance with fully passive wavelength multiplexing integration, supporting high-fidelity uniformity and projecting scalability to 1.468 Tb/s. This work promises advancements in high-performance optoelectronic devices for next-generation AI-driven data centers and 5G-XG networks.

physics.optics↗

arXiv2025

Enhancing Linear Attention with Residual Learning

Linear attention offers a linear-time alternative to self-attention but often struggles to capture long-range patterns. We revisit linear attention through a prediction-correction lens and show that prevalent variants can be written as a combination of a historical prediction and a single-token correction, which creates an expressivity bottleneck. To address this bottleneck, we introduce Residual Linear Attention (RLA), a framework that equips linear attention with an explicit residual-fitting mechanism. RLA maintains an auxiliary recurrent state that learns to accumulate residual errors over time and correct the base prediction. We further instantiate a delta-rule version, Residual Delta Net (RDN), incorporating adaptive gating and residual clipping for enhanced correction control and stability. Our implementation leverages highly optimized linear attention kernels and preserves linear time and memory. Across language modeling and recall-intensive evaluations, RLA and RDN consistently outperform their respective baselines and other modern linear-attention methods, narrowing the gap to standard Transformers while retaining linear scaling.

cs.LG↗

arXiv2025

Miniaturized Computational Dispersion-Engineered Silicon Photonic Vernier Caliper Spectrometer

The development of miniaturized spectrometers for cost-effective mobile applications remains challenging, as small footprints fundamentally degrade bandwidth and resolution. Typically, achieving high resolution necessitates extended and sophisticated optical paths for spectral decorrelation. These restrict bandwidth both physically (through resonant wavelength periodicity constraints) and mathematically (due to resulting ill-conditioned large matrix factorizations). Here, we report a spectrometer using a computational dispersion-engineered silicon photonic Vernier caliper. This deterministic design enables periodicity-suppressed orthogonal measurements by nature, thus overcoming the bandwidth-resolution-footprint limit of current chip-scale spectrometers. Leveraging the dispersion-engineered Vernier subwavelength grating microrings and factorization-free matrix computation, a spectral resolution of 1.4 pm is achieved throughout a bandwidth of >160 nm with a footprint of <55*35 {\mu}m2 in a single detection channel,establishing the highest bandwidth-to-resolution-to-footprint ratio (>57 {\mu}m-2) demonstrated to date. Furthermore, broadband densely overlapped molecular absorption spectra of hydrogen cyanide are precisely measured, resolving 49 R- and P-branch lines with linewidths ranging from 15 to 86 pm which is fundamentally challenging for compressive sensing approaches. Our chip-scale spectrometer provides a new path toward precise and real-time multi-species spectral analysis and facilitates their commercialization.

physics.optics↗