arXiv subjects

Han Chen

Publications and source records attributed to Han Chen.

At least 19 recordsLinked to original sources

arXiv2026

TempCloze: Can Video-LLMs Identify the Missing Middle?

Temporal reasoning benchmarks for Video-LLMs are often mediated by language, leaving room for linguistic shortcuts from option wording, answer correlations, or language priors. To reduce such shortcuts, we introduce TempCloze, a video cloze benchmark for evaluating visual temporal reasoning in Video-LLMs. Given the beginning and ending clips of a video, models must identify the true missing middle from four candidates. TempCloze contains 1,521 carefully filtered videos from seven sources, mainly long-take and egocentric videos. We construct same-source distractors along three dimensions: Semantic asks what event should happen, Alignment probes when it should occur, and Progression tests how it should unfold, while shared scenes and objects reduce appearance cues. Our evaluation of 10 proprietary and 21 open-source Video-LLMs reveals Alignment as the primary bottleneck: models often recognize plausible semantic content and local event progression but struggle with temporal alignment. We further conduct error pattern and behavioral sensitivity analyses on TempCloze-Mixed and TempCloze-Hard with four representative models to examine where errors arise and how candidate order, context direction, visible span, frame density, and test-time scaling influence model choices.

cs.CV↗

arXiv2026

Representing Visual Evidence for Item Difficulty Prediction: Visual Textualization and Image-Native Modeling

Predicting item difficulty from content can provide an initial estimate for newly developed questions before sufficient student responses are available. Existing approaches typically represent the question stem and answer choices as text. When mathematics items contain visual components, a common pipeline first textualizes that evidence and then applies a text predictor. We ask: how should visual evidence be represented for item difficulty prediction? We compare question text alone, visual textualization, which expresses visual evidence in language, and image-native modeling, which retains the original image. Using Eedi items with difficulty calibrated from student responses, we train large language models (LLMs) and vision-language models (VLMs) directly for difficulty regression. Both visual interfaces achieve the lowest point estimates, although the leading systems cannot be reliably ordered. Open-VLM textualization yields lower RMSE point estimates for all evaluated LLMs, while broader adaptation does so for all image-native VLMs. Test-time interventions show dependence on the paired full-item image, but do not isolate the additional visual component. The two visual interfaces also make partially complementary item-level errors and differ substantially in computational workflow. Thus, textualization should not be treated as the only practical interface: image-native modeling is a competitive alternative whose effectiveness depends on how the VLM is adapted.

cs.CL↗

arXiv2026

Markov Chain Monte Carlo with Diffusion Paths

Sampling from multimodal distributions is a longstanding challenge for classical local Markov chain Monte Carlo (MCMC) methods. A popular remedy is to introduce a sequence of intermediate distributions that interpolate between the target and a simpler reference. The classical choice, tempering, raises the density to a power, but distorts the relative weights of asymmetric modes and can lead to poor mixing. We instead propose interpolating along the diffusion path, the marginals of a noising diffusion process that carries the target toward a Gaussian. This path preserves the relative weights of the modes and enjoys favorable mixing properties, which we make precise through a spectral-gap analysis of the corresponding ideal transition kernel. Sampling along the path requires its intermediate scores, which can be estimated from the unnormalized target through variational approaches, yielding only an approximate sampler. To remove the resulting bias, we introduce the Metropolis-adjusted diffusion path (MAD-Path) sampler, which corrects the diffusion-path proposal in an augmented path space and leaves the target invariant regardless of the accuracy of the learned score or the discretization error. We further quantify how these two errors affect the acceptance probability, providing guidance for practical tuning. Experiments on a range of Bayesian posteriors show that MAD-Path improves global exploration and mode-weight estimation relative to tempering-based MCMC methods and unadjusted diffusion samplers.

stat.CO↗

arXiv2026

LLMs Struggle to Measure What Distinguishes Students of Different Proficiency Levels: A Study of Item Discrimination in Reading Comprehension Assessment

Existing work on LLM-based educational assessment has focused largely on item difficulty, but difficulty alone does not indicate whether an item meaningfully distinguishes higher- from lower-proficiency students. Item discrimination captures this complementary and fundamental psychometric property. We investigate whether LLMs can predict human item discrimination from assessment content. We evaluate 42 proprietary and open-weight LLMs using two complementary approaches. Direct discrimination prediction asks models to explicitly predict an item's discrimination value, while response-based proxy estimation treats LLM answers as synthetic responses and applies a Classical Test Theory (CTT)-inspired item-rest calculation. Direct predictions show weak alignment with human item discrimination. The response-based proxy provides a stronger but still limited ranking signal, reaching a CEFR-stratified rank correlation of 0.231. Further analysis shows that this correlation comes mainly from differences across models rather than proficiency prompts that reliably simulate students at different ability levels. Current LLMs therefore contain some discrimination-relevant information, but they do not yet reliably model the ability-conditioned human response behavior that gives item discrimination its psychometric meaning.

cs.CL↗

arXiv2026

Monogenity of Fibonacci polynomials and Lucas polynomials

We investigate the monogenity of irreducible factors of the Fibonacci polynomials $F_n(x)$ and the Lucas polynomials $L_n(x)$. Our main results show that for every odd positive integer $n$, all irreducible factors of $F_n(x)$ are monogenic, and for every even positive integer $n$, all irreducible factors of $L_n(x)$ are monogenic.

math.NT↗

arXiv2026

RW-TTT: Batched Serving for Request-Owned Test-Time Training State

Test-time training (TTT) adapts an LLM during generation by reading and updating request-owned state, such as fast weights, low-rank deltas, or streaming learner state. This breaks batched LLM serving, which assumes shared static weights: serial execution is correct but slow, while naive batching can corrupt request state. We formulate this problem as read-write TTT serving and present RW-TTT , which tags each decode step with its owner, version, and READ/WRITE effect, batches only compatible phases, and commits updates only to the owner. On one GPU with eight fast-weight InPlace-TTT streams, RW-TTT reaches 274.61 aggregate tok/s, 9.31x over sequential serving and 3.44x over per-stream replicas under the same memory budget. It preserves behavior on RULER, a long-context benchmark, and passes owner/version checks.

cs.LG↗

arXiv2026

MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing

Memory is a fundamental component for long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, many stateful systems retain sequential autoregressive extraction or state-dependent maintenance on the write path, delaying when new evidence becomes queryable. To address these challenges, we present MemForest, a memory framework that reformulates agent memory as a write-efficient temporal data-management problem. MemForest breaks the sequential bottleneck via parallel extraction, decoupling memory construction into concurrent, independent operations. We further introduce MemTree, a hierarchical temporal index that organizes memory as time-ordered trees and replaces global rewrites with localized dirty-path refresh. Dirty summaries can be refreshed in parallel across nodes and trees. End-to-end work remains proportional to incoming content; the logarithmic bound applies only to structural insertion and level-dependent refresh depth in balanced trees. We evaluate MemForest on two long-context benchmarks, LongMemEval-S and LoCoMo. Experiments use Qwen3-4B, Qwen3-30B, and Gemma-4-12B-IT. With Qwen3-30B, MemForest reaches 81.8 percent pass at 1 on LongMemEval-S, while its input-normalized build rate is 6.0 times that of EverMemOS. On LoCoMo categories 1 to 4, it reaches 84.09 percent, within 0.13 percentage points of EverMemOS; on a matched conversation, its build rate is 9.5 times higher. These results show that MemForest reduces memory-freshness latency while retaining strong answer quality.

cs.DB↗

arXiv2026

ROSE: An Intent-Centered Evaluation Metric for NL2SQL

Execution Accuracy (EX), the widely used metric for evaluating the effectiveness of Natural Language to SQL (NL2SQL) solutions, is becoming increasingly unreliable. It is sensitive to syntactic variation, ignores that questions may admit multiple interpretations, and is easily misled by erroneous ground-truth SQL. To address this, we introduce ROSE, an intent-centered metric that focuses on whether the predicted SQL answers the question, rather than consistency with the ground-truth SQL under the reference-dependent paradigm. ROSE employs an adversarial Prover-Refuter cascade: SQL Prover assesses the semantic correctness of a predicted SQL against the user's intent independently, while Adversarial Refuter uses the ground-truth SQL as evidence to challenge and refine this judgment. On our expert-aligned validation set ROSE-VEC, ROSE achieves the best agreement with human experts, outperforming the next-best metric by nearly 24% in Cohen's Kappa. We also conduct a largescale re-evaluation of 19 NL2SQL methods, revealing four valuable insights. We release ROSE and ROSE-VEC to facilitate more reliable NL2SQL research.

cs.DB↗

arXiv2026

Strain-released epitaxy of GaN enabled by compliant single-crystalline metal foils

Heteroepitaxy conventionally relies on rigid crystalline substrates, implicitly assuming that lattice and thermal mismatch must be accommodated within the epitaxial layer, leading to residual strain and defects that worsen with increasing substrate size. Here we demonstrate a substrate-mediated strain-partitioning regime in which lattice and thermal mismatch are preferentially partitioned into the substrate rather than stored in the epitaxial layer. We report the epitaxial growth of single-crystalline GaN on mechanically compliant yet crystallographically ordered single-crystalline copper foils. Atomic-resolution microscopy, geometric phase analysis and density functional theory reveal that mismatch-induced stress is primarily screened by elastic deformation of the Cu lattice, accompanied by localized interfacial slip confined to a few atomic layers, leaving the AlN and GaN epilayers nearly strain-free despite large nominal mismatch. Leveraging this strain-released epitaxial platform, we further demonstrate dense GaN micro-light-emitting diode arrays that benefit from efficient vertical electrical conduction and thermal dissipation enabled by the metallic substrate. By establishing compliant single-crystal metal foils as a new substrate class, this work identifies mechanical contrast as an underexplored governing parameter in heteroepitaxial design, with implications extending beyond GaN.

cond-mat.mtrl-sci↗

arXiv2026

Artificial intelligence-driven improvement of hospital logistics management resilience: a practical exploration based on H Hospital

Hospital logistics management faces growing pressure from internal operations and external emergencies, with artificial intelligence (AI) holding untapped potential to boost its resilience. This study explores AI's role in enhancing logistics resilience via a mixed-methods case study of H Hospital, combining 12 key informant interviews and a full survey of 151 logistics staff, with the PDCA cycle as the analytical framework. Thematic and quantitative analyses (hierarchical regression, structural equation modeling) were adopted for data analysis. Results showed 94.7% staff perceived AI application, with the strongest improvements in equipment maintenance (41.1%) and resource allocation (33.1%), but limited effects in emergency response (18.54%) and risk management (15.23%). AI integration positively correlated with logistics resilience (\b{eta}=0.642, p<0.001), with management system adaptability as a positive moderator (\b{eta}=0.208, p<0.01). The PDCA cycle fully mediated the AI-resilience relationship. We conclude AI effectively enhances logistics resilience, dependent on adaptive management systems and structured continuous improvement mechanisms. Targeted strategies are proposed to form an AI-driven closed-loop resilience mechanism, offering empirical guidance for AI-hospital logistics integration and resilient health system construction.

cs.AI↗

arXiv2026

SunnyParking: Multi-Shot Trajectory Generation and Motion State Awareness for Human-like Parking

Autonomous parking fundamentally differs from on-road driving due to its frequent direction changes and complex maneuvering requirements. However, existing End-to-End (E2E) planning methods often simplify the parking task into a geometric path regression problem, neglecting explicit modeling of the vehicle's kinematic state. This "dimensionality deficiency" easily leads to physically infeasible trajectories and deviates from real human driving behavior, particularly at critical gear-shift points in multi-shot parking scenarios. In this paper, we propose SunnyParking, a novel dual-branch E2E architecture that achieves motion state awareness by jointly predicting spatial trajectories and discrete motion state sequences (e.g., forward/reverse). Additionally, we introduce a Fourier feature-based representation of target parking slots to overcome the resolution limitations of traditional bird's-eye view (BEV) approaches, enabling high-precision target interactions. Experimental results demonstrate that our framework generates more robust and human-like trajectories in complex multi-shot parking scenarios, while significantly improving gear-shift point localization accuracy compared to state-of-the-art methods. We open-source a new parking dataset of the CARLA simulator, specifically designed to evaluate full prediction capabilities under complex maneuvers.

cs.RO↗

arXiv2026

Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical deduction. Traditional Reinforcement Learning (RL) attempts to mitigate this by introducing a ``think-before-speak'' paradigm. However, applying RL directly in high-dimensional, discrete token spaces faces three inherent challenges: sample-inefficient rollouts, high gradient estimation variance, and the risk of catastrophic forgetting. To fundamentally address these structural bottlenecks, we propose \textbf{DeepLatent Reasoning (DLR)}, a latent-space bidirectional contrastive reinforcement learning framework. This framework shifts the trial-and-error cost from expensive token-level full sequence generation to the continuous latent manifold. Specifically, we introduce a lightweight assistant model to efficiently sample $K$ reasoning chain encodings within the latent space. These encodings are filtered via a dual reward mechanism based on correctness and formatting; only high-value latent trajectories are fed into a \textbf{frozen main model} for single-pass decoding. To maximize reasoning diversity while maintaining coherence, we design a contrastive learning objective to enable directed exploration within the latent space. Since the main model parameters remain frozen during optimization, this method mathematically eliminates catastrophic forgetting. Experiments demonstrate that under comparable GPU computational budgets, DLR achieves more stable training convergence, supports longer-horizon reasoning chains, and facilitates the sustainable accumulation of reasoning capabilities, providing a viable path toward reliable and scalable reinforcement learning for LLMs.

cs.LG↗

arXiv2025

Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction

Accurate estimation of item (question or task) difficulty is critical for educational assessment but suffers from the cold start problem. While Large Language Models demonstrate superhuman problem-solving capabilities, it remains an open question whether they can perceive the cognitive struggles of human learners. In this work, we present a large-scale empirical analysis of Human-AI Difficulty Alignment for over 20 models across diverse domains such as medical knowledge and mathematical reasoning. Our findings reveal a systematic misalignment where scaling up model size is not reliably helpful; instead of aligning with humans, models converge toward a shared machine consensus. We observe that high performance often impedes accurate difficulty estimation, as models struggle to simulate the capability limitations of students even when being explicitly prompted to adopt specific proficiency levels. Furthermore, we identify a critical lack of introspection, as models fail to predict their own limitations. These results suggest that general problem-solving capability does not imply an understanding of human cognitive struggles, highlighting the challenge of using current models for automated difficulty prediction.

cs.CL↗

arXiv2025

STARS: Semantic Tokens with Augmented Representations for Recommendation at Scale

Real-world ecommerce recommender systems must deliver relevant items under strict tens-of-milliseconds latency constraints despite challenges such as cold-start products, rapidly shifting user intent, and dynamic context including seasonality, holidays, and promotions. We introduce STARS, a transformer-based sequential recommendation framework built for large-scale, low-latency ecommerce settings. STARS combines several innovations: dual-memory user embeddings that separate long-term preferences from short-term session intent; semantic item tokens that fuse pretrained text embeddings, learnable deltas, and LLM-derived attribute tags, strengthening content-based matching, long-tail coverage, and cold-start performance; context-aware scoring with learned calendar and event offsets; and a latency-conscious two-stage retrieval pipeline that performs offline embedding generation and online maximum inner-product search with filtering, enabling tens-of-milliseconds response times. In offline evaluations on production-scale data, STARS improves Hit@5 by more than 75 percent relative to our existing LambdaMART system. A large-scale A/B test on 6 million visits shows statistically significant lifts, including Total Orders +0.8%, Add-to-Cart on Home +2.0%, and Visits per User +0.5%. These results demonstrate that combining semantic enrichment, multi-intent modeling, and deployment-oriented design can yield state-of-the-art recommendation quality in real-world environments without sacrificing serving efficiency.

cs.IR↗

arXiv2025

A Provably Efficient Method for Tensor Ring Decomposition and Its Applications

We present the first deterministic, finite-step algorithm for exact tensor ring (TR) decomposition. Our method leverages blockwise simultaneous diagonalization to recover TR cores from a limited number of tensor observations, under a dimension condition requiring each mode size to be at least quadratic in the TR rank and under a genericity assumption on the cores, thereby providing both algebraic insight and practical efficiency. We extend the approach to the symmetric TR setting, where parameter complexity is significantly reduced and applications arise naturally in physics-based modeling and exchangeable data analysis. To handle noisy observations, we develop a robust recovery scheme that couples our initialization with alternating least squares, achieving faster convergence and improved accuracy compared to classical methods. As applications, we obtain new algorithms for questions in other domains where tensor ring decomposition is a key primitive, namely matrix product state tomography in quantum information and provable learning of pushforward distributions in the foundations of machine learning. These contributions advance the algorithmic foundations of TR decomposition and open new opportunities for scalable tensor network computation.

math.NA↗

arXiv2025

Causal Inference on Sequential Treatments via Tensor Completion

Marginal Structural Models (MSMs) are popular for causal inference of sequential treatments in longitudinal observational studies, which however are sensitive to model misspecification. To achieve flexible modeling, we envision the potential outcomes to form a three-dimensional tensor indexed by subject, time, and treatment regime and propose a tensorized history-restricted MSM (HRMSM). The semi-parametric tensor factor model allows us to leverage the underlying low-rank structure of the potential outcomes tensor and exploit the pre-treatment covariate information to recover the counterfactual outcomes. We incorporate the inverse probability of treatment weighting in the loss function for tensor completion to adjust for time-varying confounding. Theoretically, a non-asymptotic upper bound on the Frobenius norm error for the proposed estimator is provided. Empirically, simulation studies show that the proposed tensor completion approach outperforms the parametric HRMSM and existing matrix/tensor completion methods. Finally, we illustrate the practical utility of the proposed approach to study the effect of ventilation on organ dysfunction from the Medical Information Mart for Intensive Care database.

stat.ME↗

arXiv2025

R-Capsule: Compressing High-Level Plans for Efficient Large Language Model Reasoning

Chain-of-Thought (CoT) prompting helps Large Language Models (LLMs) tackle complex reasoning by eliciting explicit step-by-step rationales. However, CoT's verbosity increases latency and memory usage and may propagate early errors across long chains. We propose the Reasoning Capsule (R-Capsule), a framework that aims to combine the efficiency of latent reasoning with the transparency of explicit CoT. The core idea is to compress the high-level plan into a small set of learned latent tokens (a Reasoning Capsule) while keeping execution steps lightweight or explicit. This hybrid approach is inspired by the Information Bottleneck (IB) principle, where we encourage the capsule to be approximately minimal yet sufficient for the task. Minimality is encouraged via a low-capacity bottleneck, which helps improve efficiency. Sufficiency is encouraged via a dual objective: a primary task loss for answer accuracy and an auxiliary plan-reconstruction loss that encourages the capsule to faithfully represent the original textual plan. The reconstruction objective helps ground the latent space, thereby improving interpretability and reducing the use of uninformative shortcuts. Our framework strikes a balance between efficiency, accuracy, and interpretability, thereby reducing the visible token footprint of reasoning while maintaining or improving accuracy on complex benchmarks. Our codes are available at: https://anonymous.4open.science/r/Reasoning-Capsule-7BE0

cs.CL↗

arXiv2025

HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis

The advancement of graph-based malware analysis is critically limited by the absence of large-scale datasets that capture the inherent hierarchical structure of software. Existing methods often oversimplify programs into single level graphs, failing to model the crucial semantic relationship between high-level functional interactions and low-level instruction logic. To bridge this gap, we introduce \dataset, the largest public hierarchical graph dataset for malware analysis, comprising over \textbf{200M} Control Flow Graphs (CFGs) nested within \textbf{595K} Function Call Graphs (FCGs). This two-level representation preserves structural semantics essential for building robust detectors resilient to code obfuscation and malware evolution. We demonstrate HiGraph's utility through a large-scale analysis that reveals distinct structural properties of benign and malicious software, establishing it as a foundational benchmark for the community. The dataset and tools are publicly available at https://higraph.org.

cs.LG↗