Search arXiv⌕ Search

arXiv subjects

Shuo Sun

Publications and source records attributed to Shuo Sun.

At least 19 recordsLinked to original sources
arXiv2026

Online Stochastic Allocation with Increasing Returns

We study online allocation with increasing returns, where an uncertain number of customers arrive sequentially and can be irrevocably assigned to any product with remaining capacity. Each assignment earns a base reward plus a bonus that is nondecreasing in the number of previous assignments to the same product. Prior work has focused primarily on fixed or diminishing returns. Under increasing returns, the central challenge is that concentrating assignments can unlock large future rewards, while a different product may be preferable if arrivals stop early. We show that classical approaches, including greedy and natural LP-based rounding algorithms, can perform arbitrarily poorly, even with homogeneous bonuses. We evaluate performance through competitive ratios relative to the hindsight offline optimum. For homogeneous bonuses, we establish a tight competitive ratio of $1/2$. For arbitrary heterogeneous bonuses, however, no online algorithm can guarantee a competitive ratio greater than $1/m$, where $m$ is the number of products. By imposing discrete concavity on the bonus functions, we limit the concentration of rewards in later assignments and restore constant guarantees. Under this structure, we develop a re-solving framework that repeatedly selects a planning horizon, constructs a feasible allocation plan from the current state, and executes its assignments in a specific order. For arbitrary arrival distributions, we design distribution-oblivious deterministic and randomized algorithms with competitive ratios of $0.2537$ and $0.3864$, respectively. For known increasing-failure-rate (IFR) arrival distributions, we exploit distributional information to obtain a deterministic $1/2$-competitive algorithm.

cs.DS↗
arXiv2026

FilingLoop: Evaluating and Evolving LLM Agents for Corporate Disclosure Review and Revision

Public disclosure repositories such as SEC EDGAR support informed investment through web access to corporate filings. Supporting their review with language model agents requires discovering unstated deficiencies across related documents, acquiring missing company facts, and verifying that requested revisions satisfy evidence-backed requirements. Existing financial question-answering evaluations provide limited evidence of these interactive capabilities. We introduce \textbf{FilingLoop}, an interactive benchmark and a self-evolving agent framework for corporate disclosure review and revision. Grounded in historical U.S.\ Securities and Exchange Commission correspondence, FilingLoop reconstructs 380 predominantly IPO review tasks from 96 companies under distinct information constraints. An evaluator separate from the acting agents scores final filings and responses against 6,099 eligible requirements and audits unsupported claims and harmful revisions. Our framework couples iterative review and revision within each case with procedural learning across cases, converting requirement-level evaluation feedback into role-specific guidance without updating model weights. Updates affect only subsequent cases, allowing procedural adaptation to be assessed without retrying scored tasks. On the evaluated stream, evolution increases requirement fulfillment from 24.28\% to 27.96\% and full comment resolution from 16.90\% to 20.75\%, with a 5.8\% increase in total cost over the fixed-policy variant. FilingLoop connects the concerns an agent discovers with the company facts it obtains and the revisions it commits, providing requirement-level feedback for procedures used in later review tasks.

cs.AI↗
arXiv2026

Beyond Profit Rankings: Identifying, Understanding, and Evaluating Smart Money in Prediction Markets

Prediction markets have emerged as an important mechanism for aggregating information and trading beliefs about future events. The transparency of on-chain transactions has enabled investors to identify historically profitable wallets, commonly referred to as smart money, and replicate their trading activities through copy trading. However, despite the growing popularity of smart-money tracking, systematic research on these wallets' trading behavior, profitability persistence, and the economic feasibility of following their trades remains limited. To address this gap, we conduct a comprehensive empirical study of Polymarket, the most popular decentralized prediction market, by reconstructing wallet-level trading activities from on-chain transactions, position changes, market histories, and settlement outcomes. We first examine the distribution and persistence of historical profitability using statistical analysis and logistic regression, and further characterize heterogeneous trading strategies through multidimensional behavioral profiling and unsupervised clustering. Building on these findings, we develop an evidence-grounded multi-agent research framework that integrates wallet behavior, market conditions, and real-world information to generate interpretable and verifiable explanations of individual trades. Finally, we implement a real-time copy-trading system and evaluate its practical feasibility through order-book-aware paper trading and live on-chain execution. Our findings reveal substantial behavioral heterogeneity among historically profitable wallets and highlight the challenges of translating observed trading performance into replicable economic returns.

cs.CE↗
arXiv2026

A Multi-Asset Dataset and Tail-Risk Framework for DeFi Yield Trading Derivatives

Yield trading has emerged as a pivotal innovation in Decentralized Finance (DeFi) by decoupling principal from yield streams to enhance capital efficiency. Despite its significance, the field lacks fine-grained datasets for systematic empirical analysis. We address this gap by constructing the first large-scale benchmark dataset for Pendle, the pioneering on-chain interest rate derivatives protocol, spanning 24 months across 340 active markets with complete lifecycle observations. Our analysis reveals a structural market transition toward stablecoin-dominated "flight-to-quality" dynamics. To tackle the heavy-tailed nature of yield data, we propose Tail-MSE, an asymmetric loss function that prioritizes tail risk awareness through dynamic penalty weighting. Experiments across six state-of-the-art time series models demonstrate consistent improvements in volatility forecasting robustness, enabling the Tail-MSE Sniper strategy to achieve superior risk-adjusted returns in over half of all markets.

cs.CE↗
arXiv2026

Delta-Doped GeV$^-$ in diamond with isotope resolvable optical spectra

Group IV color centers in diamond -- silicon, germanium, tin, and lead-vacancy centers -- are a promising platform for quantum networking. Typical Group-IV creation utilizes ion implantation during diamond growth that leaves the color centers with a broad depth distribution and damage-induced strain inhomogeneity. Deterministic placement and damage reduction in Group IV generation are essential for improving this platform. In this letter, we report on the localization of germanium-vacancy (GeV$^-$) to a $<$ 10 nm layer via the timed injection of GeH$_4$ during microwave plasma chemical vapor deposition. In this layer we have realized 17 ppm of Ge and a strain-free environment for the GeV$^-$. Subsequent electron irradiation and annealing have generated a sheet density of 0.12 GeV$^-$/$μ$m$^2$. The minimal damage from color center generation mitigates spectral inhomogeneity and allows spectral resolution of isotopic clusters, with the best cluster having an inhomogeneous distribution of 2.14 GHz and an average linewidth of $47 \pm 11$ MHz. Our study gives insight into formation dynamics of GeV$^-$ in delta-doped systems and estimates our vacancy to GeV$^-$ yield to be $\geq$ 90%, establishing an athermal nearest-neighbor formation model. We further characterized the spin $T_2^*$ and set a lower bound of 730 ns, limited by a paramagnetic defect.

quant-ph↗
arXiv2026

Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models

HopChain has shown on still images that multi-hop data synthesis improves vision-language reasoning, because long chain-of-thought reasoning exposes errors that compound across steps, while most data used for reinforcement learning with verifiable rewards (RLVR) rarely demands a chain of visual evidence, so these weaknesses are likely to stay unexposed. We observe the same problem in video, where this framework has not yet been explored. We therefore build Video-HopChain, a dataset of 22,550 multi-hop video questions over 13,378 videos, together with a held-out benchmark of 1,000 questions. Each question chains three to six yes/no questions about moments in one video, and each yields one of two integers depending on its answer. The final answer is the sum of these integers, so an exact match on that sum gives the verifiable reward that RLVR needs. We first train Qwen3-VL-8B with GRPO on a standard video dataset, and a second stage on Video-HopChain then raises the mean over eight video understanding and reasoning benchmarks from 55.4 to 57.9 and improves every one of them. Training on such a dataset, however, exposes a known limitation of GRPO: its learning signal comes from the reward variance within a group, so hard questions whose rollouts are all incorrect and easy questions whose rollouts are all correct both leave the group with no gradient. To recover these groups at the same compute budget, we introduce Confidence-Gated Exploration (CGE). With 8 rollouts per question, CGE samples the first 4 as usual. If these 4 are either all correct or all incorrect, it samples the last 4 with the policy's most confident token masked inside the reasoning span, and removes the masked positions from the loss while all 8 rollouts enter the advantage. With CGE, the mean rises further to 59.3. We release the dataset, the checkpoint, and the data generation and training code.

cs.CV↗
arXiv2026

MorphingNet: Symbolic Regression Where the Network Is the Formula

We introduce MorphingNet, a network for symbolic regression (SR) whose units change their function continuously. Instead of searching over expressions built from a fixed operator library, MorphingNet trains the form of each function as a parameter, so SR becomes one continuous optimization problem. Its units are either pole-free rational functions or complex exponential--logarithm functions, which move between exponentials, sinusoids, damped oscillations, power laws and logarithms as their parameters change. The network is a readable formula at every step of training, and no operator library is needed to train it; a structure-recovery step afterwards rewrites the trained formula into short elementary expressions. Training is dense linear algebra, so it is GPU-friendly and scales to large data. MorphingNet achieves state-of-the-art accuracy on SRBench, recovers most generating formulas on synthetic benchmarks, and on large data is up to two orders of magnitude faster than the strongest search method. By turning the search for a formula into the training of a network, MorphingNet offers a new paradigm for SR and for scientific discovery from data.

cs.LG↗
arXiv2026

Dense Dynamic Scene Reconstruction and Camera Pose Estimation from Multi-View Videos

We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a setting that arises naturally when multiple observers capture a shared event. Prior approaches either handle only single-camera input or require rigidly mounted, pre-calibrated camera rigs, limiting their practical applicability. We propose a two-stage optimization framework that decouples the task into robust camera tracking and dense depth refinement. In the first stage, we extend single-camera visual SLAM to the multi-camera setting by constructing a spatiotemporal connection graph that exploits both intra-camera temporal continuity and inter-camera spatial overlap, enabling consistent scale and robust tracking. To ensure robustness under limited overlap, we introduce a wide-baseline initialization strategy using feed-forward reconstruction models. In the second stage, we refine depth and camera poses by optimizing dense inter- and intra-camera consistency using wide-baseline optical flow. Additionally, we introduce MultiCamRobolab, a new real-world dataset with ground-truth poses from a motion capture system. Finally, we demonstrate that our method significantly outperforms state-of-the-art feed-forward models on both synthetic and real-world benchmarks, while requiring less memory.

cs.CV↗
arXiv2026

STOCK-JEPA: Prior-Anchored Latent Revision Representation Learning in Equity Markets

Learning effective representations helps characterize the structure and dynamics of equity markets from financial data with a low signal-to-noise ratio. Black-box deep models can capture complex patterns but may overfit sample noise and lack explicit economic structure. Meanwhile, classic linear financial models provide interpretable references, but their oversimplified assumptions leave non-linear signals uncaptured. To combine the strengths of these two directions, we propose Stock-JEPA, a joint-embedding predictive framework that learns predictable incremental revisions relative to a point-in-time financial prior. First, we leverage a low-complexity financial model to produce fixed statistics summarizing multi-horizon return and risk. A prior projector then maps these statistics into the target encoder's latent space as an anchor. Second, we design a context-conditioned revision predictor to estimate the future representation's predictable displacement from the anchor. Separate losses update the two branches: the anchor learns from prior statistics, while the revision captures additional predictable information from historical context. Third, we freeze all representation modules and train a downstream readout, evaluating its forecasts through cross-sectional ranking and portfolio performance. Theoretically, we prove that optimal revision reduces the prior anchor's expected squared error for the same future representation by exactly $\mathbb{E}[\|\boldsymbolΔ\|_2^2]$. This non-negative gain is the expected squared magnitude of the additional signal predictable from historical context. Experimentally, Stock-JEPA outperforms 13 strong baselines across large-scale China and U.S. equity universes on 5 key evaluation metrics. Ablation studies and representation analysis further demonstrate the value of the learned revisions for representation learning in equity markets.

cs.LG↗
arXiv2026

Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs

When an omnimodal large language model accepts a question whose textual premise contradicts what it actually sees or hears, does the failure lie in perception or in action? Recent omnimodal models are positioned as perception-grounded agents that jointly process video, audio, and text, yet a basic form of grounding remains untested: catching a textual claim that conflicts with the model's own sensory input. We introduce IMAVB, a curated 500-clip benchmark of long-form movies with a 2x2 design crossing target modality (vision, audio) and premise condition (standard, misleading), which lets us measure conflict detection separately from ordinary multimodal comprehension. Across eight open-source omnimodal LLMs and Gemini 3.1 Pro, we document a Representation-Action Gap: hidden states reliably encode premise-perception mismatches even when the same models almost never reject the false claim in their outputs. Behaviorally, models fall into two failure modes: under-rejection, in which they answer misleading questions as if the false premise were true; and over-rejection, in which they reject more often but also reject standard questions, sacrificing ordinary comprehension accuracy. The gap is modality-asymmetric (audio grounding underperforms vision) and prompt-resistant across seven variants. As an initial diagnostic intervention, a probe-guided logit adjustment (PGLA) re-injects the encoded mismatch signal into decoding and consistently improves rejection behavior. Together, these results suggest the bottleneck for omnimodal grounding lies in translation, not perception.

cs.AI↗
arXiv2026

Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs

Audio large language models (Audio LLMs) exhibit systematic failures in transcribing code-switching speech despite strong multilingual capabilities. Focusing on English-Mandarin, we identify three failure modes: language omission, translation-instead-of-transcription, and hallucination. We apply Direct Preference Optimization (DPO) to align models, constructing preference pairs in which chosen responses preserve mixed-language content while rejected responses mimic failure patterns. Training three Audio LLMs on 100K pairs (570 hours), we observe consistent behavioral shifts: models learn to preserve language composition rather than translating when prompted for transcription. This alignment yields MER reductions up to 89.6% (in-distribution) and 20.0% (out-of-distribution). Our findings suggest DPO can effectively elicit correct code-switching transcription behavior from multilingual Audio LLMs.

cs.CL↗
arXiv2026

Efficient Application of Tensor Network Operators to Tensor Network States Through Successive Deterministic Compression

We introduce an algorithm to apply tree tensor network operators to tree tensor network states followed by compression. Especially when applying a matrix product operator to matrix product states, this serves as a key subroutine in tensor network algorithms. We name the method successive deterministic compression (SDC). We compare SDC to existing operator application and compression algorithms in benchmarks involving random tensor network operators and states, as well as circuit simulation with standard entangling gates. We find that successive deterministic compression is consistently among the best-performing techniques when the tensor network state (after the operator application) is not highly compressible. Our results also highlight the flexibility of general tree tensor network structures for simulating circuits with long-range entanglement.

quant-ph↗
arXiv2026

SemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions

Rule decisions such as content moderation, advertising compliance, and eligibility checks combine several conditions, exemptions, and missing-information cases, and an error can be fixed only once the failing condition is known. We introduce SemTree, a framework that represents a rule decision as a semantic decision tree: each node is a natural-language question with explicit Yes/No/Unknown criteria, a pluggable semantic judge answers it, and the branching structure is compiled on the answers that this judge actually gives. The executed path is the reasoning behind every decision, so errors are repaired where they occur: a reviewer corrects a single node and replays the rule, corrected nodes become training labels for the judge, and a tool-using LLM editor revises questions and subtrees while observing execution results. On all 8,276 ShARC test cases, a tree executed by a hosted judge reaches 67.70% accuracy with 2.99 questions per case, on par with asking the same judge for the final label (68.23%); an earlier tree compiled for a different judge scores 47.87% when executed by this judge, while a new tree compiled on this judge's answers to a 12-question initial pool already scores 64.39%. Node-level repair raises BANKING77 accuracy from 82.04% to 86.16%, an explicit exemption node cuts the false positives of a Chinese e-commerce moderation clause from 24 to 5, and a trained editor raises the development accuracy of edited trees from 64.47% to 73.35%.

cs.LG↗
arXiv2026

Unlocking the Forecasting Economy: A Suite of Datasets for the Full Lifecycle of Prediction Market: [Experiments \& Analysis]

Prediction markets are markets for trading claims on universal future events (e.g., presidential elections). Fueled by a meteoric surge with over \$50 billion trading volume, they have emerged as a promising forecasting mechanism, where their prices provide continuously updated signals of collective beliefs. In decentralized platforms (e.g., Polymarket), the prediction market lifecycle include six stages: market creation, token registration, trading, oracle interaction, dispute, and final settlement. However, comprehensively tracking this complete pipeline remains a major challenge, as the underlying data are severely fragmented across heterogeneous on-chain smart contracts and off-chain sources. To fill this critical gap, we present the first continuously synchronized dataset suite for the full-lifecycle of decentralized prediction markets. To achieve large-scale cross-source integration, incomplete linkage, and continuous synchronization, we build a unified relational data system that integrates three canonical layers: i) market metadata, ii) fill-level trading records, iii) oracle-resolution events, through identifier resolution, on-chain recovery, and incremental updates. The resulting dataset spans from October 2020 to update-to-date and comprise more than 3.29 million market records, over 1.90 billion order execution records, and nearly 21 million oracle events. We describe the data model, collection pipeline, and consistency mechanisms that make the datasets reproducible and extensible. We further demonstrate its utility for multiple communities through NBA outcome calibration for sport traders, CPI expectation reconstruction for economists, and oracle-risk analysis for blockchain researchers. A public website with dataset access, interactive visualizations, and lightweight LLM-assisted exploration tools are publicly available at https://www.polymonitor.club.

cs.LG↗
arXiv2026

AlphaOpsBench: Benchmarking End-to-End Alpha Strategy Operationalization in Prediction Markets

Large language models increasingly generate quantitative trading strategies, yet existing benchmarks assume standardized assets, numerical features, or directly compilable strategy representations---assumptions that prediction-market strategies violate, since a coarse idea may leave the traded outcome, causal information source, signal definition, threshold, sizing, order policy, exit, and settlement behavior unspecified. We introduce \textsc{AlphaOpsBench}, which evaluates end-to-end operationalization from source-grounded economic hypotheses to auditable executable programs over 581 source-preserving strategy records and a lifecycle-scale Polymarket dataset with 1.28 million binary markets, 183.6 million cleaned executions, settlement evidence, and limit-order-book history, comparing Direct generation against a Staged design-then-code protocol. In a corrected independent-generation study over 36 controlled tasks and 24 preregistered real strategies, strict end-to-end validity remains rare: Direct and Staged obtain 35/180 and 20/180 canonical passes on the controlled cohort and no confirmed pass on the real cohort, and repeated generations vary substantially in model-owned economic choices. By contrast, 775,725 of 783,655 scheduled historical replays complete, showing that replayability is a far weaker property than source-faithful operationalization. Financial outcomes depend on the declared execution model and available historical evidence, and fee and liquidity experiments show that execution costs alter subsequent trading paths rather than acting only as ex-post deductions. \textsc{AlphaOpsBench} thus separates strategy fidelity, behavioral validity, historical executability, and financial performance in an evidence-aware benchmark for LLM-based quantitative research in prediction markets.

cs.CE↗
arXiv2026

Constructions of LCPs and LCD codes from twisted Reed-Solomon codes

Linear complementary pairs (LCPs) and linear complementary dual (LCD) codes have important applications in orthogonal direct-sum masking (ODSM), which provides effective countermeasures against side-channel attacks and fault-injection attacks. While LCD codes have been extensively investigated, comparatively fewer results are available for general LCPs. In this paper, we further investigate LCPs of twisted Reed--Solomon (TRS) codes. We derive necessary conditions for two TRS codes to form an LCP and establish several sufficient conditions and explicit constructions. We also study LCD codes constructed from TRS codes and investigate the security parameters of the resulting LCPs. Furthermore, under suitable conditions, we obtain MDS LCPs of TRS codes.

cs.IT↗
arXiv2026

SEA-SpeechBench: A Large-Scale Multitask Benchmark for Speech Understanding Across Southeast Asia

The rapid advancement of audio and multimodal large language models has unlocked transformative speech understanding capabilities, yet evaluation frameworks remain predominantly English-centric, leaving Southeast Asian (SEA) languages critically underrepresented. We introduce SEA-SpeechBench, to the best of our knowledge, the first large-scale multitask benchmark that evaluates speech understanding in 11 SEA languages through 97,194 samples across 99 evaluation sets and 597 hours of curated audio data. Our benchmark comprises 9 diverse tasks across 3 categories: speech processing (automatic speech recognition, speech translation, spoken question answering), paralinguistic analysis (emotion, gender, age, speaker recognition), and temporal understanding, a novel dimension featuring timestamped content queries and temporal localization within extended audio sequences up to 3 minutes. We implement multilingual prompting in both native SEA languages and English to reflect user interactions with audio-language models. Evaluation of leading open-source and proprietary systems reveals marked performance gaps. Across all models, performance remains underwhelming on temporal understanding, emotion recognition, and speech translation. Prompting in low-resource languages such as Burmese and Tamil lags behind English by up to 41 percentage points. Our findings expose critical model limitations and underscore the need for inclusive model development. The SEA-SpeechBench benchmark is available at https://zwenyu.github.io/SEA-SpeechBench/.

cs.CL↗
arXiv2026

HODAgent: Towards On-Demand, Responsive Humanoids for Physical World Human Interaction

We propose HODAgent, a System-2 embodied agent for humanoid robots in service settings, addressing situated intent, responsive execution, task revision, and outcome verification. Its semi-duplex architecture integrates an Env-Interactor, Planner, Executor, and hierarchical Memory to maintain coherent interaction, planning, and task state during service episodes. This allows handling new requests during motion, retaining progress, revising actions, and grounding closure in execution outcomes. A shared interface connects simulation and physical robots (Unitree G1), isolating platform-specific control. In an interactive simulation with 164 cases, HODAgent achieves 84.8% and 91.5% Joint Success under two VLM backbones, outperforming baselines by 9.8 and 18.9 points. On physical robots, pass rates are 92% (atomic), 72% (composite), and 63.3% (complete tasks). On multiple embodied benchmarks, it improves over baselines by 0.7-9.0 points. Results show a unified System-2 agent enables adaptive humanoid service across simulation and reality.

cs.RO↗