arXiv subjects

Dawei Liu

Publications and source records attributed to Dawei Liu.

At least 19 recordsLinked to original sources

arXiv2026

Self-powered InAs nanowire detector arrays for extended-SWIR spectrometry at room temperature

Spectral sensing in the extended shortwave infrared (e-SWIR) is important for molecular analysis, infrared imaging, and machine vision, motivating the development of compact spectrometers for broader applications. However, conventional commercial off-the-shelf spectrometers in this wavelength region are expensive and bulky due to their reliance on external dispersive optics/filters and/or cryogenic accessories. Other emerging computational spectrometers are based on Si and InGaAs photodetectors that remain focused on the visible and near-infrared, with few detector platforms operating in the e-SWIR regime that simultaneously provide broadband sensitivity, low-noise room-temperature operation, and diverse spectral signatures for accurate identification and reconstruction. Here, we report a room-temperature e-SWIR computational spectrometer based on InAs/InP core-shell nanowire photodetector arrays with geometry-encoded spectral responses. The detectors exhibit self-powered broadband photoresponse across the 1--3 $\mu$m range, with responsivity up to 0.215 A W$^{-1}$, detectivity up to $1.6 \times 10^{9}$ cm Hz$^{1/2}$ W$^{-1}$, and microsecond response times. The excellent detector performance is leveraged to demonstrate filter-free spectral reconstruction using a compact multipixel photodetector array device. This enables high-accuracy molecular absorption spectrum reconstruction and hyperspectral imaging. Our results indicate that InAs nanowire arrays are a promising platform for compact computational spectrometry and imaging in the e-SWIR at room temperature.

physics.optics↗

arXiv2026

Dr. Claw: An AI Scientist Workspace for Vibe Research

Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fragments across chat tools, IDEs, terminals, and writing environments, and the decisions that make it auditable are rarely preserved. We present Dr. Claw, an open-source workspace that wraps existing coding-agent executors in a controllable and auditable human-in-the-loop workflow rather than introducing another autonomous agent. Persistent state objects, a reusable skill library, and multi-executor coordination link human decisions to AI execution, turning planning, execution, and writing into one traceable, recoverable loop. We demonstrate Dr. Claw through an interactive three-view scenario and a failure-recovery walkthrough, and evaluate it against a bare command-line agent sharing the same backend executor, so the comparison contrasts the whole orchestration layer (task graph, state objects, and skill library) with the agent it wraps. Holding the executor fixed, Dr. Claw scores higher on research completeness while persisting an auditable, recoverable process trail. Demo access: repository https://github.com/OpenLAIR/dr-claw, released under AGPL-3.0 with GPL-3.0 upstream components.

cs.AI↗

arXiv2026

Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning

We introduce Mobius-v0, an architecture that comprises a globally shared Memory (FFN) that stores knowledge vectors and multiple Reasoners (Self-Attn) that iteratively achieve compositional reasoning. Using hidden states as cache and carrier, reasoners repeatedly query memory for required knowledge-vectors, while the knowledge is transmitted back to reasoning operators. Through this knowledge-reasoning-separation architecture, Mobius achieves better knowledge compression and reasoning efficiency. Built upon Mobius-v0 architecture: 1) Our 7B model trained-from-scratch achieves similar downstream score as a 7B Transformer baseline with 62.6% of baseline's training data. 2) Our Intern-S2-Mobius, continually-pretrained from Qwen3.5-35B, achieves similar downstream score while delivering nearly 4x end-to-end inference speedup.

cs.AI↗

arXiv2026

UniJEPA: A Unified Joint-Embedding Predictive Architecture for Task-Agnostic Visual World Modeling

Joint-Embedding Predictive Architectures (JEPAs) have emerged as a principled framework for self-supervised learning of world models in compact latent spaces, yet existing methods are fragmented: some predict masked parts of a single image in latent space (I-JEPA), others learn to predict global photometric transformations (Image World Models), while video-scale JEPAs predict future temporal states and are post-trained for action-conditioned planning (V-JEPA~2, DINO-World, DINO-WM). These objectives are treated as distinct recipes with separate encoders, predictors, and anti-collapse regularizers, hindering a single model from unifying image-level and video-level world modeling. We present UniJEPA, a unified JEPA that jointly learns photometric prediction (image-level transformations) and temporal prediction (video-level next-state dynamics) in one shared latent space. A single end-to-end objective, composed of a next-embedding prediction loss and a Gaussian regularizer, yields a provably anti-collapse encoder-predictor pair trainable from raw pixels without EMA, stop-gradient, or pre-trained encoders. We show that the same latent space supports controllable abstraction: photometric prediction learns invariant structure while temporal prediction learns equivariant dynamics. After action-conditioned post-training on offline trajectories, UniJEPA enables zero-shot planning by treating goal features as prediction targets. On image, video, and control benchmarks, UniJEPA matches or surpasses task-specific JEPAs while requiring a single loss hyperparameter, and plans up to tens of times faster than generative world models at comparable accuracy.

cs.CV↗

arXiv2026

PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory

Long-context reasoning remains a critical bottleneck for large language models, as recent recurrent-memory approaches face two inherent challenges: sequential chunk-wise updates can overwrite early critical evidence with later irrelevant content, and serial inter-chunk dependencies limit parallelism and cause latency to increase with context length. To address these issues, we propose PI-Mem (Parallel-Iterative Memory), a mechanism that processes all chunks in parallel and iteratively refines a shared memory over a bounded number of turns. In each turn, PI-Mem reads all chunks in parallel conditioned on the current memory, selects new or complementary evidence from each chunk, and merges the selected evidence into a compact shared memory for the next turn. To discourage redundant turns, we optimize the workflow through reinforcement learning with an auxiliary turn-efficiency reward, enabling the model to adaptively exit once sufficient evidence has been accumulated. We evaluate PI-Mem with Qwen3.5-35B-A3B and Qwen2.5-7B on the HotpotQA benchmark across context lengths up to 3.6 million tokens and find that it outperforms the recurrent-memory baseline by +6.25 and +7.81 absolute points while achieving 6.1$\times$ and 2.1$\times$ inference speedups, respectively. These results demonstrate that PI-Mem breaks the accuracy--efficiency trade-off in long-context reasoning and provides a scalable approach to complex multi-hop question answering over extremely long documents.

cs.CL↗

arXiv2026

DiffuseAgent-MI: Distributionally-Grounded,Tool-Integrated Self-Evolving Agents for Faithful Visual Reasoning

Tool-integrated vision-language agents have made remarkable progress on compositional and multi-step visual reasoning. Yet their outputs frequently exhibit unfaithfulness: the stated reasoning path diverges from the computation that actually produced the answer, undermining reliability in safety-critical applications. We present DiffuseAgent-MI, a self-evolving agent whose perceptual grounding is governed by a KL-minimal energy model over feature units, providing a distributional view of visual mechanistic interpretability. The agent learns an energy landscape that softly constrains generated samples to lie near the native prior conditioned on the chosen interpretable unit, closing the gap between the explanation and the internal representation. A verifier then supplies trajectory-level faithfulness rewards, and a repair branch re-conditions the energy when the verifier flags an unfaithful step. On GeoQA, SciVis, VQA-v2 and an in-house multimodal reasoning set, DiffuseAgent-MI improves accuracy by up to 5.1 points over prior self-evolving agents while more than doubling mutual-information faithfulness and human-interpretability agreement. Our analysis shows the energy term and the verifier are complementary: the former guarantees distributional faithfulness, the latter trajectory-level faithfulness, and only their combination closes both gaps.

cs.CV↗

arXiv2026

COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows

Agents are increasingly used to construct workflows and assist humans in completing recurring tasks more efficiently. As these workflows become repeated and domain-specific, agent memory and reusable skills become increasingly important: agents should be able to recall workflow patterns, execution constraints, and user preferences from previous runs. We study this problem in workflow-based image generation and introduce COMFYCLAW, an agentic skill evolution harness for controlling ComfyUI workflows. COMFYCLAW formulates workflow construction as typed graph editing, exposes tools organized by construction stage, automatically reverts invalid edits, and uses a region-level vision-language model (VLM) verifier to translate visual failures into actionable repair suggestions. The framework further evolves a progressively disclosed skill library, where trajectories, execution errors, and verifier feedback from previous runs are distilled into reusable Agent Skills. Across four benchmark splits, three agent models, and two image backbones, COMFYCLAW achieves the best average image-generation evaluation score across all six agent configurations, outperforming a verifier-only baseline without skill evolution. Human annotations further show that annotators prefer COMFYCLAW over variants without skill evolution. Our results suggest that skill evolution is an effective mechanism for improving agent reliability and performance in recurring visual workflow construction.

cs.AI↗

arXiv2026

A Cookbook of 3D Vision: Data, Learning Paradigms, and Application

3D vision has rapidly evolved, driven by increasingly diverse data representations, learning paradigms, and modeling strategies. Yet the field remains fragmented across representations and benchmarks, making it difficult to develop unified perspectives on efficiency, fidelity, and scalability. This work provides a data-centric taxonomy of 3D vision that connects geometric representations, datasets, learning frameworks, and applications within a single conceptual map. We begin by analysing the principal structural representations of 3D data--point clouds, meshes, voxels, and 3D Gaussians--along with their acquisition pipelines. We then examine how dataset design, benchmark construction, and supervision regimes shape recent advances, spanning 2D-supervised 3D learning, implicit neural representations, and 4D world modeling. Through this integrative lens, we clarify the relationships among representations, learning paradigms, and downstream tasks in reconstruction, generation, and video modeling, offering a consolidated view of emerging trends toward balancing efficiency and fidelity and toward multimodal geometric grounding.

cs.CV↗

arXiv2026

SHM-Agents: A Generalist-Specialist Integrated Agent System for Structural Health Monitoring

Artificial intelligence is increasingly used to simplify complex tasks. In engineering applications of structural health monitoring (SHM), existing specialized algorithms, while effective, often face high implementation barriers, limited interoperability and complex training procedures. To overcome these challenges, this paper proposes SHM-Agents, a generalist-specialist agent system that integrates the reasoning and planning abilities of large language models with the problem-solving strengths of specialized algorithms. SHM-Agents enables end-to-end execution of single and combined SHM tasks via natural language, supports deep learning pre-training to simplify deployment and allows flexible expansion through a modular design. Experiments on a long-span cable-stayed bridge show that SHM-Agents can accurately and efficiently perform diverse SHM tasks, including data anomaly diagnosis and recovery, signal processing, statistical analysis, modal identification, damage identification, finite element model updating, vehicle load modeling, response calculation, reliability assessment, fatigue estimation and bridge knowledge Q\&A.

cs.MA↗

arXiv2026

Tuning Plasmonic Metasurfaces via Phase Change Material Substrates for Modulating Reactivity in Light-Driven Reactions

Phase change materials provide a powerful platform for dynamically modulating optical responses in nanophotonic systems. While plasmonic metasurfaces have been widely employed to enhance photocatalytic efficiency and promote particular light-driven reactions, active and dynamical control over reaction pathways within a single device remains challenging. Here, we report a phase-induced tunable metasurface that tailors photoexcited electron populations through mode hybridization, enabling selective control over the reactivity of light-driven chemical processes. By exploiting thermally induced refractive-index switching in a Sb2S3 cavity, the plasmonic resonance strength of Au nanodisks is actively tuned via cavity-plasmon hybridization. This reconfiguration modulates the product yield of methylene blue degradation by a factor of 2.4, suppressing to 0.45 in the crystalline phase and enhancing to 1.09 in the amorphous phase. Importantly, this reconfigurable platform enables dynamic control of the reaction yield using a single metasurface architecture under identical illumination conditions. Our approach establishes a dynamically programmable light-driven reaction platform capable of precisely manipulating reaction reactivity, offering new opportunities for selective photocatalysis in complex multibranch reaction systems.

physics.optics↗

arXiv2026

Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills

Modern LLM agents increasingly rely on reusable skills, and as they interact with personal applications, web browsers, and other interfaces, skill libraries can scale to thousands of skills. Scaling to larger skill sets introduces two key challenges. First, loading the full skill set saturates the context window, driving up token costs, hallucination, and latency. Second, semantic retrieval surfaces topically relevant skills but misses their prerequisite chain of upstream and downstream skills, creating a prerequisite gap that leaves the retrieved bundle execution-incomplete. In this paper, we present Graph-of-Skills (GoS), an inference-time structural retrieval layer for large skill libraries. GoS constructs an executable skill graph offline from skill packages, then at inference time retrieves a bounded, dependency-aware skill bundle through hybrid semantic-lexical seeding, reverse-aware Personalized PageRank, and context-budgeted hydration. On SkillsBench and ALFWorld, GoS consistently delivers substantial reward improvements and token savings across three model families (Claude Sonnet 4.5, MiniMax M2.7, and GPT-5.2 Codex). On SkillsBench, GoS achieves a peak reward increase of 25.55% while reducing total tokens by 56.72% over the vanilla full skill-loading baseline using GPT-5.2 Codex. Ablations confirm this pattern across skill libraries from 200 to 2,000 skills.

cs.AI↗

arXiv2025

Light matter interaction in van der Waals heterostructures with Mie voids

Recently introduced concept of Mie voids allows to enhance the field localization inside air cavities embedded in high-index materials. Mie voids provide an alternative approach to conventional dielectric resonators that confine optical fields within bulk high-index materials. Building on this concept, here we present a hybrid photonic platform that integrates monolayer WS2 with Mie void resonators patterned in a high-index Bi2Te3 substrate. By carefully aligning the dipolar void resonance with the excitonic transition of WS2, we achieve substantially enhanced photoluminescence and second-harmonic generation. Far-field imaging of the harmonic fields reveals spatially resolved hotspots that directly map localized resonant modes, with their positions tunable by cavity geometry and pump wavelength. This approach enables real-space control of nonlinear emission at the single-resonator level, offering a robust and reconfigurable platform for next-generation nonlinear photonics and surface-enhanced optical sensing.

physics.optics↗

arXiv2025

SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding

Block-wise discrete diffusion offers an attractive balance between parallel generation and causal dependency modeling, making it a promising backbone for vision-language modeling. However, its practical adoption has been limited by high training cost, slow convergence, and instability, which have so far kept it behind strong autoregressive (AR) baselines. We present \textbf{SDAR-VL}, the first systematic application of block-wise discrete diffusion to large-scale vision-language understanding (VLU), together with an \emph{integrated framework for efficient and stable training}. This framework unifies three components: (1) \textbf{Asynchronous Block-wise Noise Scheduling} to diversify supervision within each batch; (2) \textbf{Effective Mask Ratio Scaling} for unbiased loss normalization under stochastic masking; and (3) a \textbf{Progressive Beta Noise Curriculum} that increases effective mask coverage while preserving corruption diversity. Experiments on 21 single-image, multi-image, and video benchmarks show that SDAR-VL consistently improves \emph{training efficiency}, \emph{convergence stability}, and \emph{task performance} over conventional block diffusion. On this evaluation suite, SDAR-VL sets a new state of the art among diffusion-based vision-language models and, under matched settings, matches or surpasses strong AR baselines such as LLaVA-OneVision as well as the global diffusion baseline LLaDA-V, establishing block-wise diffusion as a practical backbone for VLU.

cs.CV↗

arXiv2025

Exploration of Embodied Space Experience through Umbilical Interaction: A Grounded Theory Approach

This paper critiques the limits of human-centered design in HCI, proposing a shift toward Interface-Centered Design. Drawing on Hookway's philosophy of interfaces, phenomenology, and embodied interaction, we created Umbilink, an umbilical interaction device simulating a uterine environment with tactile sensors and rhythmic feedback to induce a pre-subjectivized state of sensory reduction. Participants' experiences were captured through semi-structured interviews and analyzed with grounded theory. Our contributions are: (1) introducing the novel interface type of Umbilical Interaction; (2) demonstrating the cognitive value of materialized interfaces in a human-interface-environment relation; (3) highlighting the design role of wearing rituals as liminal experiences. As a pilot study, this design suggests imaginative applications in healing, meditation, and sleep, while offering a speculative tool for future interface research.

cs.HC↗

arXiv2025

SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation

We propose SDAR, a Synergistic Diffusion-Autoregression paradigm that unifies the training efficiency of autoregressive models with the parallel inference capability of diffusion. Instead of costly end-to-end diffusion training, SDAR performs a lightweight paradigm conversion that transforms a well-trained autoregressive (AR) model into a blockwise diffusion model through brief, data-efficient adaptation. During inference, SDAR generates sequences autoregressively across blocks for global coherence while decoding all tokens within each block in parallel via a discrete diffusion process. Extensive experiments show that AR models remain substantially more compute-efficient than masked diffusion models, providing a strong foundation for adaptation. Building on this insight, SDAR achieves efficient AR-to-diffusion conversion with minimal cost, preserving AR-level performance while enabling parallel generation. Scaling studies across dense and Mixture-of-Experts architectures confirm that SDAR scales without compromise: larger models exhibit stronger robustness to block size and decoding thresholds, yielding greater speedups without accuracy loss. Beyond efficiency, SDAR demonstrates enhanced reasoning and domain adaptability. Our 30B MoE model surpasses its AR counterpart on challenging scientific reasoning benchmarks such as GPQA and ChemBench, and gains further improvements under test-time scaling methods like majority voting and pass@k. Together, these results establish SDAR as a practical paradigm that combines the strengths of autoregression and diffusion for scalable, high-throughput reasoning.

cs.LG↗

arXiv2025

Spatiotemporal Topological Combs for Robust High-Dimensional Information Transmission

Sculpting light across its independent degrees of freedom-from orbital angular momentum to the discrete wavelengths of optical frequency combs-has unlocked vast communication bandwidth by enabling massively parallel information channels. However, the Shannon-Hartley theorem sets a hard limit by tying channel capacity to the trade-off between SNR and rate, a central challenge in communication. Inspired by lock-in amplification in electronics, we encode data on THz optical burst carriers so the signal resides beyond the conventional noise band, yielding exceptional robustness. By leveraging a programmable all-degree-of-freedom (All-DoF) modulator, we generate a spatiotemporal topological comb (ST-Comb) that structures light into a vast, highentropy state space for high-dimensional information encoding. Crucially, we find that the associated topological winding number is preserved under diverse perturbations, ensuring stable information encoding and retrieval. This paradigm illustrates how structured light can simultaneously expand channel dimensionality and maintain robustness, charting a pathway to chip-scale, reconfigurable photonic platforms for the PHz era, while also opening previously inaccessible regimes of light-matter interaction.

physics.optics↗

arXiv2025

Polarization-Sensitive Au-TiO2 Nanopillars for Tailored Photocatalytic Activity

Plasmonic metasurfaces play a crucial role in resonance-driven photocatalytic reactions by effectively enhancing reactivity via localized surface plasmon resonances. Catalytic activity can be selectively modulated by tuning the strength of plasmonic resonances through two primary non-thermal mechanisms: near-field enhancement and hot carrier injection, which govern the population of energetic carrier excited or injected into unoccupied molecular orbitals. We developed a set of polarization-sensitive metasurfaces consisting of elliptical Au-TiO2 nanopillars, specifically designed to plasmonically modulate the reactivity of a model reaction: the photocatalytic degradation of methylene blue. Surface-enhanced Raman spectroscopy reveals a polarization-dependent reaction yield in real-time, modulating from 4.7 (transverse electric polarization) to 9.98 (transverse magnetic polarization) in 10 s period, as quantified by the integrated area of the 480 cm-1 Raman peak and correlated with enhanced absorption at 633 nm. The single metasurface configuration enables continuous tuning of photocatalytic reactivity via active control of plasmonic resonance strength, as evidenced by the positive correlation between measured absorption and product yield. This dynamic approach provides a route to selectively enhance or suppress resonance-driven reactions, which can be further leveraged to achieve selectivity in multibranch reactions, guiding product yields toward desired outcomes.

physics.optics↗

arXiv2025

Multiple Object Stitching for Unsupervised Representation Learning

Contrastive learning for single object centric images has achieved remarkable progress on unsupervised representation, but suffering inferior performance on the widespread images with multiple objects. In this paper, we propose a simple but effective method, Multiple Object Stitching (MOS), to refine the unsupervised representation for multi-object images. Specifically, we construct the multi-object images by stitching the single object centric ones, where the objects in the synthesized multi-object images are predetermined. Hence, compared to the existing contrastive methods, our method provides additional object correspondences between multi-object images without human annotations. In this manner, our method pays more attention to the representations of each object in multi-object image, thus providing more detailed representations for complicated downstream tasks, such as object detection and semantic segmentation. Experimental results on ImageNet, CIFAR and COCO datasets demonstrate that our proposed method achieves the leading unsupervised representation performance on both single object centric images and multi-object ones. The source code is available at https://github.com/visresearch/MultipleObjectStitching.

cs.CV↗