Search arXiv⌕ Search

arXiv subjects

Tianyi Jiang

Publications and source records attributed to Tianyi Jiang.

At least 19 recordsLinked to original sources
arXiv2026

EnvSched: Environment-Aware Scheduling for Rollout-Efficient Agent Reinforcement Learning

As executable environments for language agents scale, generating and verifying their rollouts becomes increasingly expensive. Under finite rollout budgets, this raises an important question: can data management at the environment level make agentic reinforcement learning (RL) more efficient by organizing, evaluating, and scheduling task instances together with the environments that determine their tools, states, transitions, and verification? To address this question, we introduce EnvSched (Environment-aware Scheduling), an online scheduler that learns from rollout history. EnvSched assigns scheduling value through two complementary modeling choices: exploitation prioritizes tasks likely to provide informative reward differences, while coverage spreads each batch across underobserved environments and interaction patterns. EnvSched organizes environment--task pairs as nodes in a dual-relation graph, with within-environment edges capturing task semantics and shared tool, state, and verifier structure, and cross-environment edges capturing abstract execution and reward topology. By propagating historical rollout statistics along both edge types, it predicts within-task reward variance. These predictions guide a scheduler that allocates each batch to tasks with high predicted reward variance and underobserved environments and tasks. Environment quotas and a similarity penalty further limit concentration and redundancy, yielding informative and diverse batches without additional pilot rollouts. In RL on Qwen3-8B, EnvSched achieves an average score of 48.81 across BFCL-v3, tau-Bench, and ACEBench-Agent after 40 training steps, exceeding the highest score attained by random task selection after 120 steps. It also improves downstream performance across model sizes at the same training budget.

cs.LG↗
arXiv2026

Wasserstein convergence rates for empirical measures of point processes

In this paper, we establish upper and lower bounds on the convergence rate of empirical measures of point processes under the Wasserstein distance. To this end, we first introduce a new metric on the space of finite counting measures. Unlike many existing metrics in the literature, our proposed metric incorporates the spatial locations of unmatched points. Drawing on both this new metric and existing metrics from the literature, we identify a set of common structural properties and develop a general framework for Wasserstein distances between point-process distributions based on metrics satisfying these properties. We then use this framework to investigate the convergence rates of empirical measures, providing quantitative guarantees for approximating the distribution of the underlying point process, and further establish corresponding concentration inequalities. These theoretical results may provide ingredients for constructing oracle goodness-of-fit tests for a specified point-process distribution. We also apply our theory to the approximation of Campbell measures and discuss how the resulting bounds can help assess Wasserstein-based learning of generative point-process models.

math.ST↗
arXiv2026

LogLook: Execution-Grounded Memory for Frontier-Model Robot Planners

Many manipulation tasks require a robot to remember what it has done and what it has seen. Frontier vision-language models can plan such tasks without task-specific training, but how such a planner should remember an episode is an open question. We argue that its memory must keep track of what the planner has done and learned, and must let the planner choose what to look at, since every frame costs tokens; a note rewritten at every step meets both poorly. We propose LogLook, whose execution-grounded memory lets the system keep the record, an execution log and the model's earlier notes, while the model decides where to look: frames are returned only where it expects a change, and demonstrations are skimmed before it inspects the parts it chooses. Measured with the benchmark's motion planner, LogLook matches the success of a note-only memory with 43% fewer tokens and less than half the images, and fails far fewer episodes through what it remembered or saw. With direct control, LogLook solves 93.5% of the RoboMME test set.

cs.RO↗
arXiv2026

MoLE: Mixture of Latent Experts for Complementary Visual Reasoning

Latent visual reasoning equips vision--language models with continuous intermediate states that can process visual evidence without explicit textual reasoning traces or repeated image operations. However, existing methods often allow multiple latent tokens to access the same visual evidence through shared value projections, providing no mechanism for them to extract complementary visual information; simply increasing the latent budget can therefore yield redundant latent representations. We argue that effective latent reasoning should encourage different latent tokens to extract complementary visual information, and thereby act as specialized visual experts. Based on this insight, we propose MoLE, a Mixture of Latent Experts framework that controls both what visual evidence each latent visual expert observes and how it transforms that evidence. MoLE isolates latent visual experts during evidence extraction and uses dedicated latent summary experts to aggregate the complementary representations of latent visual experts. A two-stage training pipeline first forces visual evidence through this latent pathway and then restores direct visual access, requiring neither predefined expert roles nor intermediate visual targets. Across five visual reasoning benchmarks, MoLE achieves an average score of 78.6, outperforming data-matched supervised fine-tuning by 4.9 and the strongest evaluated latent visual reasoning baseline at the same latent budget by 3.6. Representation analyses show lower latent-state similarity and more diverse visual attention, while masking the latent pathway reduces average performance by 9.2. These results demonstrate that specializing latent computation is more effective than merely increasing the number of latent tokens.

cs.CV↗
arXiv2026

CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning

Reinforcement learning enables computer-use agents to improve through interaction with real software environments, including websites and desktop applications. However, conventional deployments replicate an initialized runtime for each independent rollout, even when trajectories use the same software, incurring repeated memory and initialization costs as the number of parallel environments grows. Does an independent computer-use environment require an independent execution runtime? Our key observation is that trajectories require independent mutable state, while initialized application runtimes can be reused across concurrently evolving environments, making state the natural unit of environment independence. Guided by this observation, we introduce CUA-Sandbox, which separates private state capsules from shared runtimes through state-scoped execution and transactional lifecycle operations, including resets and branches, while retaining the original software interfaces and task evaluators. Experiments show comparable or improved task success relative to Docker, while substantially reducing rollout and resource costs. CUA-Sandbox achieves up to a 6.20x increase in rollout throughput, a 9.2x reduction in per-environment memory, and a 504x reduction in incremental storage.

cs.AI↗
arXiv2026

Copula Transformations for Data-Consistent Inversion

Data-consistent inversion (DCI) constructs probability measures whose push-forward distributions agree with observed data, while iterative data-consistent inversion (iDCI) extends this framework to generalized stochastic inverse problems by enforcing multiple push-forward constraints sequentially. Although iDCI avoids the direct approximation of high-dimensional joint densities, its relationship to the original joint DCI solution has remained unclear. In this work, we establish this relationship through copula theory. Using Sklar's theorem, we derive a factorization of the DCI update into separate marginal and dependence transformations and show that the discrepancy remaining after convergence of the iDCI algorithm is entirely characterized by the copulas associated with the observed and predicted joint distributions. This characterization motivates a copula-transformed iDCI solution, and we prove that an exact copula transformation recovers the original DCI solution. We further establish convergence results for approximate copula transformations under converging sequences of reference measures and progressively enriched feasible sets. Numerical examples demonstrate how the geometry induced by the quantity-of-interest map governs the importance of the copula transformation, illustrate an adaptive reference-measure refinement strategy for improving computational accuracy under a fixed sampling budget, and demonstrate the progressive refinement of generalized stochastic inverse problems through heterogeneous, asynchronously acquired experiments.

stat.ML↗
arXiv2026

Is EEG-to-Text Feasible in Real-World Scenarios? An In-Depth Analysis Using a Neuropsychology-Inspired Benchmark

Translating brain signals into text could restore communication for people with severe paralysis, yet practically usable systems to date rely on invasive electrocorticography (ECoG). Electroencephalography (EEG) offers a non-invasive alternative, and EEG-to-text (EEG2Text) has been widely explored. Interestingly, however, EEG2Text models generally rely on teacher-forcing evaluation; without it, they fail to generate meaningful decoding. This reliance prevents EEG2Text from being applied in real-world, non-academic settings. This has fueled numerous debates about whether EEG2Text is a meaningful direction, by extension, and whether EEG truly contains decodable linguistic information. Here, using a neuropsychology-informed paradigm, we find that existing EEG2Text benchmarks have neglected EEG instability, a flaw that has confounded inference and sparked debate. Our experiments furnish key evidence for the feasibility of teacher-forcing-free EEG2Text decoding. Accordingly, we assemble the Corpus OF Eeg-To-Text (COFETT) using a 128-channel high-density EEG cap, providing a benchmark dedicated to evaluating EEG2Text models. In comparisons with multiple existing benchmarks, COFETT achieves SOTA ability to distinguish among model performances and enables robust, teacher-forcing-free evaluation, thereby opening a path toward practical EEG2Text applications. COFETT is open sourced in https://github.com/baoyudu/COFETT.

cs.LG↗
arXiv2026

WorkDrive: Roadwork Chain of Causation for Autonomous Driving

Autonomous driving vision-language models (VLMs) struggle in roadwork zones, where familiar visual cues such as lane markings and permanent signs are altered or absent, and temporary devices such as cones and barriers redefine the drivable corridor. VLMs can detect these objects, but without explicit guidance they anchor their reasoning on familiar elements from pre-training and fail to connect work-zone observations to correct planning decisions. We propose WorkDrive, a framework that constructs perception-grounded causal reasoning for work zones and aligns it with trajectory prediction. An automated multitask perception pipeline extracts structured scene facts and injects them into a Chain-of-Causation (CoC) annotation pipeline, redirecting the annotator's attention to domain-specific elements. The resulting reasoning labels are used for supervised fine-tuning, followed by reinforcement learning with a single reward: consistency between lateral meta-actions and the predicted trajectory. On ROADWork, the largest public work-zone dataset, the proposed roadwork CoC reduces trajectory average displacement error (ADE) by 9.0\%, and consistency-based GRPO yields a further 3.0\%, achieving progressive improvement over the trajectory-only baseline. Code and data will be publicly released.

cs.CV↗
arXiv2026

SearchEyes: Towards Frontier Multimodal Deep Search Intelligence via Search World Simulation

Training multimodal search agents to perform multi-hop reasoning remains challenging due to a fundamental structural disconnect: existing pipelines construct training data, search environments, and reward signals independently, causing synthesized structural metadata to be discarded, environments to rely on irreproducible external engines, and RL rewards to remain sparse at the trajectory level. We present \textbf{SearchEyes}, which uses a typed knowledge graph as the backbone of a \emph{simulated search world} that unifies all three components. We propose \textbf{Perception-Knowledge Chains (PKC)} to sample constrained multi-hop paths over the visual-knowledge intersection of Wikidata5M, retaining hop-level entity metadata that simultaneously defines a self-contained search world and step-level reward anchors. We further propose \textbf{Hop-Anchored Policy Optimization (HaPO)}, which reuses these anchors for step-level credit assignment without a separately trained process reward model. Experiments on six multimodal knowledge-intensive benchmarks show that SearchEyes achieves state-of-the-art performance among open-source multimodal search agents, with SearchEyes-27B improving over the strongest open-source baseline by 6.2 points on average.%

cs.AI↗
arXiv2026

QuantaAlpha: An Evolutionary Framework for LLM-Driven Alpha Mining

Financial markets are noisy and non-stationary, making alpha mining highly sensitive to backtest noise and regime shifts. While recent agentic frameworks improve automation, they often lack controllable multi-round search and reliable reuse of validated experience. To address these challenges, we propose QuantaAlpha, an evolutionary alpha mining framework that treats each end-to-end mining run as a trajectory and improves factors via trajectory-level mutation and crossover. QuantaAlpha localizes suboptimal steps for targeted revision and recombines complementary high-reward segments to reuse effective patterns, enabling structured exploration and refinement across iterations. During factor generation, it enforces semantic consistency across hypothesis, factor expression, and executable code, and constrains the complexity and redundancy of the generated factor to mitigate crowding. Extensive experiments on CSI 300 show consistent gains over strong baselines and prior agentic systems. Using GPT-5.2, QuantaAlpha achieves an IC of 0.0472 with ARR of 4.68% and MDD of 11.8%. Moreover, factors mined on CSI 300 transfer effectively to CSI 500 and the S&P 500, delivering about 40.28% and 19.1% cumulative excess return over four years, respectively, which indicates strong robustness under market distribution shifts.

q-fin.ST↗
arXiv2026

Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation

Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is prohibitive for real-time deployment. Latent CoT methods attempt to close this gap by compressing reasoning into continuous hidden states, but consistently fall short of their explicit counterparts. We suggest that this is due to purely linguistic latent representations compressing a symbolic abstraction of the world, rather than the causal dynamics that actually govern driving. Thus, we present OneVL (One-step latent reasoning and planning with Vision-Language explanations), a unified VLA and World Model framework that routes reasoning through compact latent tokens supervised by dual auxiliary decoders. Alongside a language decoder that reconstructs text CoT, we introduce a visual world model decoder that predicts future-frame tokens, forcing the latent space to internalize the causal dynamics of road geometry, agent motion, and environmental change. A three-stage training pipeline progressively aligns these latents with trajectory, language, and visual objectives, ensuring stable joint optimization. In inference, the auxiliary decoders are discarded, and all latent tokens are prefilled in a single parallel pass, matching the speed of answer-only prediction. Across four benchmarks, OneVL becomes the first latent CoT method to surpass explicit CoT, delivering superior accuracy at answer-only latency. These results show that with world model supervision, latent CoT produces more generalizable representations than verbose token-by-token reasoning. Code has been open-sourced to the community. Project Page: https://xiaomi-embodied-intelligence.github.io/OneVL

cs.CV↗
arXiv2026

Iterative Data-Consistent Inversion with Multiple Push-forward Constraints

A foundational challenge in uncertainty quantification involves estimating a probability measure on the space of uncertain parameters such that its push-forward through a computational model matches an observed probability measure on the output data associated with quantities of interest (QoI). When multiple, distinct sets of observational data are available, the desired parameter measure should simultaneously satisfy multiple push-forward constraints associated with various subsets of the QoI. In this work, we present a convergent measure-theoretic framework for solving this problem based on an iterative application of Data-Consistent Inversion (DCI). We first rigorously establish the theoretical optimality of the DCI solution to the standard problem, proving that it minimizes the $f$-divergence over the space of all possible pullback measures that satisfy the push-forward constraint. This optimality property provides the foundation for our iterative DCI scheme, which is shown to converge to a solution of the multiple push-forward constraint problem. This iterative solution minimizes the cumulative $f$-divergence across all constraints and, under uniform initializations, represents the maximal entropy solution (the I-projection) onto the intersection of the solution sets. We provide a rigorous convergence analysis for the proposed method and demonstrate its practical utility through numerical examples, including a high-dimensional parameter space governed by partial differential equations, where the iterative approach robustly avoids the complexities associated with approximating high-dimensional joint observed measures.

math.OC↗
arXiv2026

KScaNN: Scalable Approximate Nearest Neighbor Search on Kunpeng

Approximate Nearest Neighbor Search (ANNS) is a cornerstone algorithm for information retrieval, recommendation systems, and machine learning applications. While x86-based architectures have historically dominated this domain, the increasing adoption of ARM-based servers in industry presents a critical need for ANNS solutions optimized on ARM architectures. A naive port of existing x86 ANNS algorithms to ARM platforms results in a substantial performance deficit, failing to leverage the unique capabilities of the underlying hardware. To address this challenge, we introduce KScaNN, a novel ANNS algorithm co-designed for the Kunpeng 920 ARM architecture. KScaNN embodies a holistic approach that synergizes sophisticated, data aware algorithmic refinements with carefully-designed hardware specific optimizations. Its core contributions include: 1) novel algorithmic techniques, including a hybrid intra-cluster search strategy and an improved PQ residual calculation method, which optimize the search process at a higher level; 2) an ML-driven adaptive search module that provides adaptive, per-query tuning of search parameters, eliminating the inefficiencies of static configurations; and 3) highly-optimized SIMD kernels for ARM that maximize hardware utilization for the critical distance computation workloads. The experimental results demonstrate that KScaNN not only closes the performance gap but establishes a new standard, achieving up to a 1.63x speedup over the fastest x86-based solution. This work provides a definitive blueprint for achieving leadership-class performance for vector search on modern ARM architectures and underscores

cs.IR↗
arXiv2026

CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions

Instruction-based multimodal image manipulation has recently made rapid progress. However, existing evaluation methods lack a systematic and human-aligned framework for assessing model performance on complex and creative editing tasks. To address this gap, we propose CREval, a fully automated question-answer (QA)-based evaluation pipeline that overcomes the incompleteness and poor interpretability of opaque Multimodal Large Language Models (MLLMs) scoring. Simultaneously, we introduce CREval-Bench, a comprehensive benchmark specifically designed for creative image manipulation under complex instructions. CREval-Bench covers three categories and nine creative dimensions, comprising over 800 editing samples and 13K evaluation queries. Leveraging this pipeline and benchmark, we systematically evaluate a diverse set of state-of-the-art open and closed-source models. The results reveal that while closed-source models generally outperform open-source ones on complex and creative tasks, all models still struggle to complete such edits effectively. In addition, user studies demonstrate strong consistency between CREval's automated metrics and human judgments. Therefore, CREval provides a reliable foundation for evaluating image editing models on complex and creative image manipulation tasks, and highlights key challenges and opportunities for future research.

cs.CV↗
arXiv2026

Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation

Large Language Models (LLMs) have demonstrated remarkable reasoning abilities on complex problems using long Chain-of-Thought (CoT) reasoning. However, they often suffer from overthinking, meaning generating unnecessarily lengthy reasoning steps for simpler problems. This issue may degrade the efficiency of the models and make them difficult to adapt the reasoning depth to the complexity of problems. To address this, we introduce a novel metric Token Entropy Cumulative Average (TECA), which measures the extent of exploration throughout the reasoning process. We further propose a novel reasoning paradigm named "Explore Briefly, Then Decide", with an associated Cumulative Entropy Regulation (CER) mechanism. This paradigm leverages TECA to help the model dynamically determine the optimal point to conclude its thought process and provide a final answer, thus achieving efficient reasoning. Experimental results across diverse mathematical benchmarks show that our approach substantially mitigates overthinking without sacrificing problem solving ability. With our thinking paradigm, the average response length decreases by up to 71% on simpler datasets, demonstrating the effectiveness of our method in creating a more efficient and adaptive reasoning process.

cs.CL↗
arXiv2026

Chain of Mindset: Reasoning with Adaptive Cognitive Modes

Human problem-solving is never the repetition of a single mindset, by which we mean a distinct mode of cognitive processing. When tackling a specific task, we do not rely on a single mindset; instead, we integrate multiple mindsets within the single solution process. However, existing LLM reasoning methods fall into a common trap: they apply the same fixed mindset across all steps, overlooking that different stages of solving the same problem require fundamentally different mindsets. This single-minded assumption prevents models from reaching the next level of intelligence. To address this limitation, we propose Chain of Mindset (CoM), a training-free agentic framework that enables step-level adaptive mindset orchestration. CoM decomposes reasoning into four functionally heterogeneous mindsets: Spatial, Convergent, Divergent, and Algorithmic. A Meta-Agent dynamically selects the optimal mindset based on the evolving reasoning state, while a bidirectional Context Gate filters cross-module information flow to maintain effectiveness and efficiency. Experiments across six challenging benchmarks spanning mathematics, code generation, scientific QA, and spatial reasoning demonstrate that CoM achieves state-of-the-art performance, outperforming the strongest baseline by 4.96\% and 4.72\% in overall accuracy on Qwen3-VL-32B-Instruct and Gemini-2.0-Flash, while balancing reasoning efficiency. Our code is publicly available at \href{https://github.com/QuantaAlpha/chain-of-mindset}{https://github.com/QuantaAlpha/chain-of-mindset}.

cs.AI↗
arXiv2026

Co-Evolution-Based Metal-Binding Residue Prediction with Graph Neural Networks

Understanding protein-metal interactions is central to structural biology, with metal ions being vital for catalysis, stability, and signal transduction. Predicting metal-binding residues and metal types remains challenging due to the structural and evolutionary complexity of proteins. Conventional sequence- and structure-based methods often fail to capture co-evolutionary constraints that reflect how residues evolve together to maintain metal-binding functionality. Recent co-evolution-based methods capture part of this information, but still underutilize the complete co-evolved residue network. To address this limitation, we introduce the Metal-Binding Graph Neural Network (MBGNN), which leverages the complete co-evolved residue network to better capture complex dependencies within protein structures. Experimental results show that MBGNN substantially outperforms the state-of-the-art co-evolution-based method MetalNet2, achieving F1 score improvements of 2.5% for binding residue identification and 3.3% for metal type classification on the MetalNet2 dataset. Its superiority is further demonstrated on both the MetalNet2 and MIonSite datasets, where it outperforms two co-evolution-based and two sequence-based methods, achieving the highest mean F1 scores across both prediction tasks. These findings highlight how integrating co-evolutionary residue networks with graph-based learning advances our ability to decode protein-metal interactions, thereby facilitating functional annotation and rational metalloprotein design. The code and data are released at https://github.com/SRastegari/MBGNN.

cs.LG↗
arXiv2026

MC-LLaVA: Multi-Concept Personalized Vision-Language Model

Current vision-language models (VLMs) show exceptional abilities across diverse tasks, such as visual question answering. To enhance user experience, recent studies have investigated VLM personalization to understand user-provided concepts. However, they mainly focus on single concepts, neglecting the existence and interplay of multiple concepts, which limits real-world applicability. This paper proposes MC-LLaVA, a multi-concept personalization paradigm. Specifically, MC-LLaVA employs a multi-concept instruction tuning strategy, effectively integrating multiple concepts in a single training step. To reduce the training costs, we propose a personalized textual prompt that uses visual token information to initialize concept tokens. Additionally, we introduce a personalized visual prompt during inference, aggregating location maps for enhanced recognition and grounding capabilities. To further push the performance upper bound, we incorporate an optional auxiliary loss, better enhancing the proposed personalized prompts. To decorate the VLM personalization research, we contribute a high-quality dataset. We carefully collect images with multiple characters and objects from movies and manually create question-answer samples for multi-concept scenarios, featuring superior diversity. Comprehensive experiments demonstrate that MC-LLaVA achieves impressive multi-concept personalized responses, paving the way for VLMs to become better user assistants. The code and dataset will be released at \href{https://github.com/arctanxarc/MC-LLaVA}{https://github.com/arctanxarc/MC-LLaVA}.

cs.CV↗