Search arXiv⌕ Search

arXiv subjects

Min Sun

Publications and source records attributed to Min Sun.

At least 19 recordsLinked to original sources
arXiv2026

Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering

Answering questions accurately and efficiently in embodied scenarios presents significant challenges due to limited computational and memory resources for Vision Language Model (VLM) inference. Existing methods adopt visual search key frame retrieval method to select critical question-related key frames for VLM input. However, visual search methods are inefficient because they require visual search among thousands of video frames for each individual user query. In this work, we propose a memory tree guided key frame selection paradigm for efficient 3D question answering in embodied scenarios. Our method leverages a compact and reusable 3D scene representation, termed MemTree3D, which supports real-time online construction leveraging camera 6-DoF poses. MemTree3D captures multi-level 3D scene information, enabling a Large Language Model to efficiently query and retrieve question-relevant key frames through our scoring-based frame selection without reprocessing the entire video stream. On OpenEQA, our method improves the LLM-Match of GPT-4o by 17.4%, LLaVA-OneVision-7B by 5.8%, outperforms existing visual search methods. Our code is available at https://github.com/hsiangwei0903/MemTree3D

cs.CV↗
arXiv2026

Human-LLM Collaborative Inductive Coding for Conceptualizing K-12 Educator AI Use

Qualitative researchers increasingly encounter interaction corpora whose scale exceeds what manual coding alone can address, and large language models (LLMs) are frequently proposed as analytic assistants. The open questions are not whether LLMs can participate in qualitative analysis but to what extent, in what phases, and under what safeguards. This article provides a detailed procedural account of a multi-phase human-LLM collaborative pipeline that adapted open, axial, and selective coding to develop a hierarchical codebook from 45,000 messages exchanged between K-12 educators and a generative AI platform. Across three phases, LLMs generated candidate labels and structured annotations at scale, while human researchers retained conceptual authority over category definitions, merging decisions, and interpretive frameworks. The resulting instrument was then tested through systematic human coding, in which three trained coders with educational domain expertise applied the codebook to an independent sample of 2,560 messages, established reliability through iterative calibration using set-valued agreement measures appropriate for multi-label annotation, and extended the instrument with five codes that the LLM-assisted phases had not surfaced. The final codebook comprises 72 items within 19 categories and six domains. We reflect on the methodological decisions the pipeline required, including the choice of a conversational unit of analysis, the treatment of the LLM as a labeling instrument rather than an interpretive agent, the measurement of intercoder agreement under multi-label coding, and the conditions under which human domain expertise remained decisive. The account is offered as an auditable template for qualitative researchers considering LLM assistance in codebook development while preserving human interpretive authority.

cs.HC↗
arXiv2026

Agreement Is Not Quality: Blind Expert Verification of Human and LLM Qualitative Coding When Human Consensus Is Not Ground Truth

Evaluations of LLM-assisted qualitative coding almost universally measure model performance as agreement with human coders, a practice that presumes human coding is the standard to approximate. This study provides empirical evidence that the presumption fails in ways agreement metrics cannot detect. Five LLM systems and three trained human coders independently applied a 72-item hierarchical codebook to 2,560 educator messages from a K-12 AI platform. Beyond conventional agreement analysis, an independent domain expert judged 855 pairwise comparisons of code sets blind to source, treating human and machine sources symmetrically. The two evaluation approaches diverge in both directions. Human-LLM agreement (mean Jaccard 0.30) falls well below human-human agreement (0.52), which standard practice would read as inferior LLM coding, yet the blind verifier preferred human and LLM coding at indistinguishable rates (51.5% vs. 48.5%, p = 0.537), and a Bradley-Terry ranking placed two LLMs above two of three human coders. For several substantive codes, human consensus encoded shared bias that the verifier rejected in favor of the LLM interpretation. Agreement-based evaluation is therefore insufficient for automation decisions, and the study demonstrates a transferable verification protocol and a code-level division-of-labor framework.

cs.HC↗
arXiv2026

Leveraging Raman response in X-cut thin-film lithium tantalate for ultrabroadband combs and polychromatic visible light

X-cut thin-film lithium tantalate (TFLT) offers a unique combination of third nonlinearity, electro-optic effects, and a high optical damage threshold. However, its strong Raman response has historically hindered broadband Kerr comb generation. Here, we leverage this inherent Raman response by engineering coupling-defined dissipation. This allows us to reconfigure the relative thresholds of Raman and Kerr processes without modifying the intrinsic microresonator dispersion. Through this coupling-engineered threshold control, we can deliberately access distinct comb states, ranging from pure Kerr combs to Raman-Kerr synergistic broadband combs. We demonstrate a Kerr comb spanning 450 nm and a Raman-Kerr comb spanning 650 nm, representing the broadest combs reported to date on X-cut TFLT platforms. Moreover, in strongly coupled devices, we show that a single near-infrared pump can generate visible emission across multiple bands (from violet to red) via cascaded second sum-frequency processes. Our work demonstrates that a strong Raman response can be transformed from a parasitic competitor into an enabling mechanism for achieving broader comb spectra and generating polychromatic visible light. This work establishes X-cut TFLT as a powerful monolithic platform for nonlinear light sources, electro-optic functions, and complex photonic systems.

physics.optics↗
arXiv2026

Seeing Once is Enough? Online Geometry-Aware Token Pruning for 3D Question Answering

Recent Multi-modal Large Language Models (MLLMs) have demonstrated remarkable performance on 2D question answering tasks. However, extending these models to the 3D question answering remains challenging, as they typically require multiple views of the scene, which incurs substantial computational cost at inference. To mitigate this issue, existing solutions rely on strategic frame selection or token-merging algorithms that require preprocessing in advance all frames of the scene, i.e., an offline fashion. In contrast, we propose the first online token-pruning method that can be integrated seamlessly with current MLLM models for 3D question answering tasks, without additional training and with lower memory usage.Our key insight is to project each input frame into a shared voxel space using depth information and camera pose, identifying spatially-overlapped regions across frames and selectively pruning redundant image tokens before they enter the language model. Our method enables efficient online processing while reducing up to 50% of token usage. We apply this approach to Qwen2.5-VL-7B and Qwen3-VL-8B, demonstrating improved performance on the ScanQA, SQA3D, and OpenEQA-HM3D benchmarks.

cs.CV↗
arXiv2026

Enhancing Part-Level Point Grounding for Any Open-Source MLLMs

Visual grounding aims to associate free-form textual queries with specific regions in an image. While recent Multimodal Large Language Models (MLLMs) have demonstrated promising capabilities in this domain, they primarily excel at object-level grounding and often struggle with part-level grounding-an essential requirement for fine-grained tasks such as robotic manipulation. In this work, we introduce a general approach that equips any open-source MLLMs with accurate 2D part-level point grounding, offering a more direct alternative to conventional grounding representations. Our method leverages the attention mechanisms inherently present in MLLMs. By synthesizing text-conditioned, grounding-aware queries within intermediate layers via the proposed Q-Synth Module, we capture target-relevant attention patterns and refine them with a lightweight Attention-to-Point Decoder, which converts these patterns into a point-centric heatmap for final prediction. Notably, all original MLLM parameters are frozen, ensuring full preservation of their pre-trained capabilities. Experiments show that our design consistently improves part-level grounding accuracy across datasets and can be seamlessly integrated into any open-source MLLMs.

cs.CV↗
arXiv2026

DiffRGD: An Inference-Time Diffusion Guidance Through Riemannian Gradient Descent

Recently, diffusion models have been widely adopted in generative modeling and have served as foundational models for many image generation tasks. To control the generation without costly re-training or fine-tuning, many works seek inference-time guidance methods to steer the latent via a differentiable objective at inference time. However, these methods cannot effectively preserve the original Gaussian distribution because they introduce distributional drift, thereby degrading the sample quality. To address this gap, we propose DiffRGD, a distribution-aware guidance framework that explicitly preserves the latent Gaussian structure. DiffRGD formulates each sampling step as a constrained optimization problem on a spherical manifold induced by the latent Gaussian distribution, and solves it efficiently via Riemannian Gradient Descent (RGD). DiffRGD is a plug-and-play method that can be seamlessly integrated into any pre-trained diffusion model. Extensive experiments demonstrate that DiffRGD outperforms previous methods in most image restoration and conditional generation tasks. Our project page is available at https://diffrgd.github.io/.

cs.CV↗
arXiv2026

The Lie We Tell: Correcting the Euclidean Fallacy in Vision Language Action Policies via Score Matching on Tangent Space

Diffusion-based Vision-Language-Action policies achieve remarkable success in robotic manipulation, yet commit a fundamental geometric error we term the $\textbf{Euclidean Fallacy}$: representing SE(3) poses as flat $\mathbb{R}^{12}$ vectors. This approximation induces (1) manifold drift violating SO(3) constraints, (2) broken equivariance under coordinate transformations, and (3) non-geodesic trajectories with excessive kinematic cost. We introduce $\textbf{Lie Diffuser Actor (LDA)}$, a diffusion framework operating intrinsically on SE(3). Our method injects noise through left-invariant SDEs, predicts scores in the tangent space, and retracts samples via the exponential map. This formulation eliminates manifold drift by construction while guaranteeing coordinate-frame equivariance and geodesic optimality. On CALVIN ABC$\rightarrow$D, LDA improves average task length from $3.27$ to $3.51$ ($+7.3\%$). We further validate our method on real robot and the results show that our methodology outperforms the baseline on majority tasks.

cs.RO↗
arXiv2026

Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering

The integration of large language models (LLMs) into educational assessment represents a transformative shift in classroom grading practices. While automated scoring systems and machine learning techniques have existed for decades, generative AI (GenAI) now enables educators to implement standards-based grading (SBG) with unprecedented efficiency and scale. This paper examines the theoretical foundations and evaluates an LLM grader that uses commercially available foundation models with context and prompt engineering to score student work against a rubric. Drawing on an empirical interrater agreement study using Massachusetts Comprehensive Assessment System (MCAS) data, we observed the Quadratic Weighted Kappa (QWK) and Proportional Reduction in Mean-Squared Error (PRMSE) across mathematics, science, and ELA, using Claude Sonnet 4, Haiku 4.5, GPT-5, and GPT-5 Mini. The results demonstrate that LLM graders, especially when based on foundational models with more parameters, achieve substantial agreement with human raters in mathematics and science assessments, while the performances vary in ELA, suggesting generic foundation models can be effective at scoring in given contexts. Additional analysis of teacher and student feedback reveals strong acceptance of AI-generated narrative feedback but skepticism toward numerical scores, suggesting that LLMs function most effectively as formative tools rather than summative evaluators. Our findings indicate that thoughtfully designed hybrid models that combine AI efficiency with teacher judgment can reduce workload, enhance feedback quality, and support equitable assessment practices without displacing professional expertise.

cs.CY↗
arXiv2026

Teacher-Authored Prompts for Configuring Student-AI Dialogue: K-12 Classroom Implementation

GenAI has rapidly entered instructional and learning settings as a teaching assistant or AI tutor. However, less is known about how pedagogical intent connects to the learning generated within these systems, especially when student-facing AI dialogues are fine-tuned through teacher orchestration in live classrooms. This study examines a classroom deployment of a "Classroom Teaching Aide" (TASD) system, which enables teachers to author both a teacher-to-AI setup prompt (instructional scaffold) and a student-facing conversation starter to launch AI-mediated classroom discussions. We analyze a multi-subject pilot conducted in Spring 2025, involving 20 participating teachers (16 of whom implemented the system), across 39 classrooms and 77 TASD settings, yielding 1,479 student-AI conversations with 878 unique students. Using platform logs, LLM coding with human validation, and post-study teacher interviews (N=10), we characterize teacher authoring choices and link them to enacted student-AI interaction outcomes. In deployment, student-AI conversations were largely aligned with instructional intent: 71% were fully on-track, and fewer than 1% were substantially off-track. However, a persistent design-enactment gap emerged for cognitive demand: 38% of conversations under-reached the teacher-targeted DOK level, approaching 50% when targeting DOK 3. The study also shows that explicit finish lines in the prompt reduced the DOK gap by 0.22 levels (p < .001), and "no direct answers" guardrails reduced AI final-answer rates by 8.5 percentage points. These findings position teacher-authored prompt layers as critical orchestration levers that translate pedagogical intent into structured student-AI dialogue, underscoring both their promise for scalable classroom integration and the need for additional supports to reliably sustain higher-order reasoning during enactment.

cs.HC↗
arXiv2026

ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints

Intelligent embodied agents should not simply follow instructions, as real-world environments often involve unexpected conditions and exceptions. However, existing methods usually focus on directly executing instructions, without considering whether the target objects can actually be manipulated, meaning they fail to assess available affordances. To address this limitation, we introduce DynAfford, a benchmark that evaluates embodied agents in dynamic environments where object affordances may change over time and are not specified in the instruction. DynAfford requires agents to perceive object states, infer implicit preconditions, and adapt their actions accordingly. To enable this capability, we introduce ADAPT, a plug-and-play module that augments existing planners with explicit affordance reasoning. Experiments demonstrate that incorporating ADAPT significantly improves robustness and task success across both seen and unseen environments. We also show that a domain-adapted, LoRA-finetuned vision-language model used as the affordance inference backend outperforms a commercial LLM (GPT-4o), highlighting the importance of task-aligned affordance grounding.

cs.AI↗
arXiv2026

High-power-handling ultra-compact acousto-optic modulators using one-dimensional topological interface states on thin-film lithium tantalate

Recent advances in integrated photonics have enabled on-chip signal modulation and processing through localized photon-phonon interactions. For acousto-optic devices, compact footprint and high efficiency are essential for dense integration, while strong power handling is critical for stable operation in demanding applications. However, it remains challenging to achieve these features simultaneously on existing integrated platforms. Here, we propose and experimentally demonstrate, for the first time on a thin-film lithium tantalate platform, an ultra-compact acousto-optic modulator based on topological interface states. Benefiting from the strong optical confinement of the topological boundary state, the device achieves a footprint of 0.13 by 0.12 mm2 and a half-wave voltage-length product of 0.491 Vcm. We further demonstrate stable acousto-optic modulation at an on-chip optical power of up to 28 dBm (630.9 mW), highlighting the strong power-handling capability of the thin-film lithium tantalate topological structure. This work provides a compact and high-power solution for microwave-to-photonic transduction and shows the potential of the thin-film lithium tantalate for robust integrated photonic systems.

physics.optics↗
arXiv2026

VLN-NF: Feasibility-Aware Vision-and-Language Navigation with False-Premise Instructions

Conventional Vision-and-Language Navigation (VLN) benchmarks assume instructions are feasible and the referenced target exists, leaving agents ill-equipped to handle false-premise goals. We introduce VLN-NF, a benchmark with false-premise instructions where the target is absent from the specified room and agents must navigate, gather evidence through in-room exploration, and explicitly output NOT-FOUND. VLN-NF is constructed via a scalable pipeline that rewrites VLN instructions using an LLM and verifies target absence with a VLM, producing plausible yet factually incorrect goals. We further propose REV-SPL to jointly evaluate room reaching, exploration coverage, and decision correctness. To address this challenge, we present ROAM, a two-stage hybrid that combines supervised room-level navigation with LLM/VLM-driven in-room exploration guided by a free-space clearance prior. ROAM achieves the best REV-SPL among compared methods, while baselines often under-explore and terminate prematurely under unreliable instructions. VLN-NF project page can be found at https://vln-nf.github.io/.

cs.RO↗
arXiv2026

Generative AI in K-12 Classrooms: A Midyear Implementation Report

This mid-year report summarizes teacher use of Colleague AI across 12 Washington State school districts from September 1 to December 31, 2025. Produced jointly by Colleague AI and AmplifyLearn.AI at the University of Washington, this report aggregates platform data and district-provided administrative records to provide an early look at how teachers engaged with AI during the first half of the 2025-26 school year. The districts vary in size from small districts with a few thousand students to large districts with up to thirty thousand students. The districts are rural, suburban, and urban. Only a subset of districts were able to provide mid-year administrative data, and findings that link teachers' use of Colleague AI to student characteristics should be interpreted as preliminary signals.

cs.CY↗
arXiv2026

Revisiting Model Stitching In the Foundation Model Era

Model stitching, connecting early layers of one model (source) to later layers of another (target) via a light stitch layer, has served as a probe of representational compatibility. Prior work finds that models trained on the same dataset remain stitchable (negligible accuracy drop) despite different initializations or objectives. We revisit stitching for Vision Foundation Models (VFMs) that vary in objectives, data, and modality mix (e.g., CLIP, DINOv2, SigLIP 2) and ask: Are heterogeneous VFMs stitchable? We introduce a systematic protocol spanning the stitch points, stitch layer families, training losses, and downstream tasks. Three findings emerge. (1) Stitch layer training matters: conventional approaches that match the intermediate features at the stitch point or optimize the task loss end-to-end struggle to retain accuracy, especially at shallow stitch points. (2) With a simple feature-matching loss at the target model's penultimate layer, heterogeneous VFMs become reliably stitchable across vision tasks. (3) For deep stitch points, the stitched model can surpass either constituent model at only a small inference overhead (for the stitch layer). Building on these findings, we further propose the VFM Stitch Tree (VST), which shares early layers across VFMs while retaining their later layers, yielding a controllable accuracy-latency trade-off for multimodal LLMs that often leverage multiple VFMs. Taken together, our study elevates stitching from a diagnostic probe to a practical recipe for integrating complementary VFM strengths and pinpointing where their representations align or diverge.

cs.CV↗
arXiv2026

Algebraic Structure Discovery for Real World Combinatorial Optimisation Problems: A General Framework from Abstract Algebra to Quotient Space Learning

Many combinatorial optimisation problems hide algebraic structures that, once exposed, shrink the search space and improve the chance of finding the global optimal solution. We present a general framework that (i) identifies algebraic structure, (ii) formalises operations, (iii) constructs quotient spaces that collapse redundant representations, and (iv) optimises directly over these reduced spaces. Across a broad family of rule-combination tasks (e.g., patient subgroup discovery and rule-based molecular screening), conjunctive rules form a monoid. Via a characteristic-vector encoding, we prove an isomorphism to the Boolean hypercube $\{0,1\}^n$ with bitwise OR, so logical AND in rules becomes bitwise OR in the encoding. This yields a principled quotient-space formulation that groups functionally equivalent rules and guides structure-aware search. On real clinical data and synthetic benchmarks, quotient-space-aware genetic algorithms recover the global optimum in 48% to 77% of runs versus 35% to 37% for standard approaches, while maintaining diversity across equivalence classes. These results show that exposing and exploiting algebraic structure offers a simple, general route to more efficient combinatorial optimisation.

cs.AI↗
arXiv2026

SceneFoundry: Generating Interactive Infinite 3D Worlds

The ability to automatically generate large-scale, interactive, and physically realistic 3D environments is crucial for advancing robotic learning and embodied intelligence. However, existing generative approaches often fail to capture the functional complexity of real-world interiors, particularly those containing articulated objects with movable parts essential for manipulation and navigation. This paper presents SceneFoundry, a language-guided diffusion framework that generates apartment-scale 3D worlds with functionally articulated furniture and semantically diverse layouts for robotic training. From natural language prompts, an LLM module controls floor layout generation, while diffusion-based posterior sampling efficiently populates the scene with articulated assets from large-scale 3D repositories. To ensure physical usability, SceneFoundry employs differentiable guidance functions to regulate object quantity, prevent articulation collisions, and maintain sufficient walkable space for robotic navigation. Extensive experiments demonstrate that our framework generates structurally valid, semantically coherent, and functionally interactive environments across diverse scene types and conditions, enabling scalable embodied AI research. project page: https://anc891203.github.io/SceneFoundry-Demo/

cs.CV↗
arXiv2025

AI as a Teaching Partner: Early Lessons from Classroom Codesign with Secondary Teachers

This report presents a comprehensive account of the Colleague AI Classroom pilot, a collaborative design (co-design) study that brought generative AI technology directly into real classrooms. In this study, AI functioned as a third agent, an active participant that mediated feedback, supported inquiry, and extended teachers' instructional reach while preserving human judgment and teacher authority. Over seven weeks in spring 2025, 21 in-service teachers from four Washington State public school districts and one independent school integrated four AI-powered features of the Colleague AI Classroom into their instruction: Teaching Aide, Assessment and AI Grading, AI Tutor, and Student Growth Insights. More than 600 students in grades 6-12 used the platform in class at the direction of their teachers, who designed and facilitated the AI activities. During the Classroom pilot, teachers were co-design partners: they planned activities, implemented them with students, and provided weekly reflections on AI's role in classroom settings. The teachers' feedback guided iterative improvements for Colleague AI. The research team captured rich data through surveys, planning and reflection forms, group meetings, one-on-one interviews, and platform usage logs to understand where AI adds instructional value and where it requires refinement.

cs.HC↗