Search arXiv⌕ Search

arXiv subjects

Haochen Zhang

Publications and source records attributed to Haochen Zhang.

At least 19 recordsLinked to original sources
arXiv2026

EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training

Vision-Language-Action Models (VLAs) inherit their visual and linguistic capabilities from Vision-Language Models (VLMs), yet most VLAs are built from off-the-shelf VLMs that are not adapted to the embodied domain, limiting their downstream performance. In this work, we propose EmbodiedMidtrain to bridge the gap between VLMs and VLAs. We first characterize the data distribution gap between them, showing that VLA data occupy compact regions that are largely separated from the broader VLM distribution, while the degree of alignment varies substantially both across and within VLM data sources. Then, we build a mid-training data engine that leverages a lightweight learnable proximity estimator to select the most VLA-aligned candidates from a large VLM pool, and produce EmbodiedMidtrain-1M, a VLM dataset that we further use to mid-train the VLM before downstream VLA fine-tuning. Experiments on both simulated robot manipulation benchmarks and real-world tasks show consistent VLA performance gains over off-the-shelf checkpoints across VLM backbones and VLA action heads. These gains extend to downstream tasks not used to guide data selection. Further analysis reveals that mid-training provides a stronger initialization for VLA fine-tuning, with gains emerging from the earliest steps and widening throughout training. Moreover, the data engine captures both dataset-level and sample-level alignment signals, favoring spatial reasoning over text-centric tasks while preserving the diversity of the VLM data. We will release all code, data and models for future research.

cs.CV↗
arXiv2026

GALA: Generation-Aware Cross-Modal Alignment for Text-to-Time-Series Synthesis

Synthesizing time series from natural language is emerging as the most expressive form of controllable time series generation. However, existing text-conditioned generators either take caption embeddings frozen from off-the-shelf text encoders, or adapt the encoder end-to-end, letting the denoising loss shape the embeddings only as a by-product. In either case, the conditioning representation is never deliberately matched to the signal modality, leaving it ill-suited to guide generation. We address this by introducing GALA: Generation-Aware cross-modaL Alignment for text conditional time series generation. GALA is a two-stage approach that first contrastively couples a pretrained text encoder with a time-series foundation model into a shared embedding space with both encoders adapted to generation by an auxiliary generative loss, and then freezes the resulting caption embedding to drive a flow-matching generator. On TSFragment-600K, spanning four domains and three fragment lengths, GALA sets a new state of the art, ranking first in 30 of 36 metric columns and reaching an average rank of 1.08/1.08/1.42 at lengths 24/48/96 against 1.92/2.00/1.75 for the strongest baseline. We further find that generator-internal text encoders force a trade-off between fidelity and caption adherence, whereas conditioning on the aligned embedding breaks it: FID, CTTP, and JFTSD all improve at once. Ablating the auxiliary loss degrades FID, CTTP and JFTSD together, it indicates the generative term is a necessary component of the alignment rather than an add-on.

cs.CL↗
arXiv2026

Understanding Gap-Dependent Regret for Optimism-Based Reinforcement Learning with Linear Function Approximation

We study gap-dependent regret for reinforcement learning with linear function approximation. While prior works have established gap-dependent guarantees in this setting, existing analyses do not apply to algorithms that achieve the nearly minimax-optimal worst-case regret bound $\tilde{O}(d\sqrt{H^3K})$, where $d$ is the feature dimension, $H$ is the horizon length, and $K$ is the number of episodes. We bridge this gap by establishing the first gap-dependent regret bound for the nearly minimax-optimal algorithm LSVI-UCB++ (He et al., 2023), with an expected regret bound $\tilde{O}(d^2H^3/Δ_{\min}+d^6H^5)$, improving the dependence on both $d$ and $H$ in the leading gap-dependent term compared with previous results. To understand the exploration cost induced by optimism, we establish a structural lower bound $Ω(d^2H^3/Δ_{\min})$ for a broad class of algorithms based on persistent ellipsoidal optimism. When specialized to LSVI-UCB++, this result shows that the leading dependence of our upper bound on $d$, $H$, and $Δ_{\min}$ is tight up to logarithmic factors. Beyond this algorithmic class, we establish a general gap-dependent lower bound $Ω(dH^3\log K/Δ_{\min})$ for arbitrary learning algorithms, showing that the logarithmic dependence on $K$ and the cubic dependence on $H$ are intrinsic to gap-dependent expected regret in linear MDPs. Together, our results substantially narrow the gap between upper and lower bounds and provide a sharper characterization of gap-dependent learning and optimism-based exploration with linear function approximation.

stat.ML↗
arXiv2026

Exact Fast Batch Simulation for Tabular Reinforcement Learning

Simulation is a fundamental computational primitive in reinforcement learning (RL), yet conventional simulation explicitly generates individual trajectories even when downstream procedures use only aggregate statistics. To address this, we develop an exact fast-simulation framework for finite-horizon tabular Markov decision processes. Our framework has two complementary modes. In direct batch simulation, a batch is represented by its aggregate Markov flow. With sufficient parallel simulation resources, this flow can be obtained by trajectory aggregation; when such simulation is unavailable or costly but the initial state and transition distributions are directly accessible, we instead generate an identically distributed flow through forward Markov-flow sampling without materializing individual trajectories. The latter reduces the simulator-side computational dependence on batch size $m$ from $O(m)$ to $O(1)$. In adaptive batch simulation, when batch length is determined by a data-dependent condition, exact multivariate-hypergeometric splitting recursively refines a candidate Markov flow while preserving the conditional law, reducing the cost dependence on $m$ from $O(m)$ to $O(\log m)$. Together, these modes accelerate simulation by keeping trajectories aggregated whenever possible and refining flows only when required to locate data-dependent boundaries. The framework applies broadly across simulator-based, offline, and online batch or stage-based RL, as illustrated with representative algorithms from each setting.

stat.ML↗
arXiv2026

Variance-Aware Fine-Grained Gap-Dependent Bounds for Online Reinforcement Learning

We study model-free online reinforcement learning (RL) for episodic tabular Markov decision processes, focusing on both gap-dependent regret and policy switching cost. While fine-grained gap-dependent analysis has been established for model-free RL algorithms using Hoeffding-type exploration bonuses, such results for model-free algorithms with variance-based exploration bonuses remain unknown, despite their superior worst-case and coarse-grained gap-dependent guarantees. In this paper, we resolve this open problem by establishing the first fine-grained gap-dependent regret upper bound for UCB-Bernstein+, a refined UCB-Bernstein algorithm, in variance-aware model-free online RL. Moreover, by integrating a stage-wise policy update design into our fine-grained framework and using refined variance-based bonuses, we achieve the best-known gap-dependent local switching cost to date. In addition, our analysis yields improved worst-case guarantees for both regret and local switching cost over the original UCB-Bernstein algorithm. Numerical experiments further demonstrate that UCB-Bernstein+ achieves favorable empirical performance in both regret and local switching cost.

stat.ML↗
arXiv2026

LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification

Time series captioning is a fundamental step in time series understanding and can also serve as the bridge between signal and natural language. Supervised fine-tuning (SFT) relies on a larger model's captions and cannot exceed their quality. Reinforcement learning (RL) can, but its rewards were designed for other modalities and other tasks, and they transfer poorly to open-ended generation in the time series domain. We address this by proposing LineupRL, a reinforcement learning with verifiable rewards (RLVR) pipeline whose reward is caption-to-series identification. The reward model is a frozen large language model (LLM) verifier that reads the generated caption and the candidate time series as raw values, never the chart, and must pick the described time series from multiple distractors. Matching is a far lighter demand on the verifier than writing questions or judging a caption, so an off-the-shelf LLM can supply the reward. Across two captioning benchmarks, and on forecasting and reconstruction where the predictor sees only the caption, LineupRL outperforms SFT and RL baselines on every metric. The 3B vision language model (VLM) trained by LineupRL also outperforms, at 1/24 of the parameters, the 72B VLM whose captions the SFT baseline is distilled from. Our case study shows that LineupRL resists reward hacking, and that the captioner it trains both traces the trend and names the values at key points.

cs.AI↗
arXiv2026

On the Divergence of Accuracy and Mechanism Consistency in Time Series World Models

A time series world model (TSWM) predicts a controlled system's state from its observed history and planned actions and exogenous inputs. Current approaches build forecasters with actions as covariates, trained and evaluated on prediction error under the executed plan. Yet world models compare unexecuted plans, but their responses to changed plans remain untested. We ask which design choices matter and whether accurate forecasters respond to changed plans as real systems do. We address both with a formalization and benchmark. The formalization separates state, actions and exogenous inputs, distinguishes continuous, mode and event actions, and introduces mechanism consistency, a metric built on declared action-state relations with known directions, such as a vasopressor raising blood pressure: it checks whether shifting an action moves the forecast in the declared direction. The benchmark consolidates eight public datasets with real actions from engineered infrastructure and clinical care, varying prediction space, plan fusion and plan encoding across seven backbones and five seeds. First, a frozen latent prediction space lowers MAE by 9.9% over observation space and gated output fusion lowers it by 12.7% over input concatenation on average, with both improving all eight datasets; temporal plan encoding changes average MAE by at most 2.2%. Second, prediction error and mechanism consistency diverge: the lowest-error configuration is at or below chance in consistency on four of five datasets with declared mechanisms, and no design choice avoids this. Finally, directional supervision, a loss penalizing the wrong-signed part of the response to a shifted action, significantly raises consistency on penalized mechanisms with no change in MAE. Together they give TSWMs a recipe: a frozen latent space and output-side fusion for accuracy, and a training objective for mechanism consistency.

cs.AI↗
arXiv2026

No Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detection

Time series anomaly detection (TSAD) plays a crucial role in healthcare, finance, industrial monitoring, and other sectors. Within and between these settings, anomalies span vastly different temporal scales, from sub-second point spikes to multi-hour drift patterns. However, most existing TSAD methods commit to a single temporal granularity, and multi-scale designs either analyze different scales in isolation or are constrained to a predefined coarse-to-fine hierarchy, both failing to sufficiently capture multi-scale interactions. To resolve this limitation, we propose Multi-Scale Autoencoder with Cross-Scale Attention for TSAD (MSCAD), a simple yet powerful semi-supervised TSAD framework founded on parallel autoencoder branches corresponding to different patch sizes. A stack of symmetric bidirectional cross-scale attention blocks enables every pair of scales to exchange information before reconstruction without allowing any single scale to be privileged. On the comprehensive TSB-AD benchmark (40 datasets, 530 series), MSCAD achieves large performance gains against 50 baselines across multiple metrics, with VUS-PR of 0.57(+9.6%) on the univariate split and 0.47(+9.3%) on the multivariate split compared to the state-of-the-art.

cs.LG↗
arXiv2026

Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models

Reasoning over language instructions in embodied tasks such as robotics often requires understanding spatial relations from a speaker's situated perspective. Humans infer such perspectives from shared environmental knowledge, activity context, and commonsense. Recent vision-language models (VLMs) appear capable of spatial reasoning, but their ability to infer a speaker's viewpoint from contextual cues and interpret situated spatial relations from that viewpoint remains unclear. We call this capability contextual observer grounding. To study this capability, we construct the Point-of-View Benchmark (POVBench), a dataset of 3D scenes and queries that disentangles Inferred, Stated, and Given forms of observer grounding in natural embodied communication. Given multi-view observations and a natural-language sentence, models must localize unseen or underspecified targets from situated spatial and contextual cues. Across state-of-the-art VLMs, localizing targets from directional language remains challenging, even when observer grounding is made explicit. We find that explicit breakdowns of observer-relative spatial reasoning improve target localization. Our project page is available at https://mimo-owl.github.io/POVBench/.

cs.CV↗
arXiv2026

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Co-work agents execute complex workflows that combine information gathering, tool use, coding, and file manipulation across many model invocations. Because cost and latency accumulate over the full episode, their practical value depends not only on peak capability but also on how efficiently that capability is delivered. Yet many steps in everyday work emphasize state tracking, coordination, recovery, and follow-through rather than frontier-scale reasoning. We present Occamy-1.0, a cost-efficient co-work model obtained by further training the post-trained Qwen3.6-35B-A3B checkpoint. We construct execution-grounded data and environments, capture replayable long-horizon trajectories across multiple harnesses, and use staged post-training to develop and consolidate complementary execution capabilities. Across a broad suite of co-work benchmarks, Occamy-1.0 is consistently among the strongest comparably sized models and remains competitive with substantially larger frontier systems on several tasks. Under our stated evaluation and pricing protocol, its aggregate performance across four representative benchmarks places it at the low-cost knee of the observed cost--performance Pareto frontier. Supporting evaluations in tool calling, coding, and instruction following further show that this specialization preserves broad agentic capability. We release the model weights and a subset of the training data to support research on practical co-work agents and agentic post-training.

cs.AI↗
arXiv2026

Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models

For robots to operate reliably in real-world environments, they need to perceive their surroundings, act, and reason about the consequences of those actions. Rapid progress in the domains of representation learning, VLA models, and world models has significantly enhanced the capabilities of robot learning systems, enabling robots to work in increasingly complex environments. However, these paradigms are typically developed in isolation, resulting in fragmented systems that struggle with generalization, long-horizon temporal reasoning and planning, and deployment in unstructured environments. In this survey, we present a unified perspective on robot learning by organizing the existing methods along three complementary axes: understanding through representation learning, acting through VLA models, and reasoning through world models. We introduce a structured taxonomy that captures key design choices in environment representation, policy learning, and predictive modeling, and summarize the recent progress in these domains. Beyond classifying the existing works, we analyze how these components interact, discuss common limitations, and highlight emerging trends towards more integrated systems. Through this lens, we identify the challenges in the domain of robot learning, including uncertainty quantification, out-of-distribution generalization, cross-embodiment transfer, long-context understanding, and long-horizon planning. We argue that these challenges arise not only from limitations within individual components but also from the lack of integration across perception, action, and reasoning. Building on this analysis, we outline future directions towards unified, physically grounded, and probabilistic robot learning to develop robust robotic systems that maintain consistent internal representations and support decision making over extended interactions in real-world environments.

cs.RO↗
arXiv2026

Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost

We study federated online reinforcement learning with linear function approximation. While recent multi-agent reinforcement learning algorithms achieve strong regret guarantees, they typically require sharing raw trajectories. This reliance incurs a communication cost that scales linearly with the number of episodes and violates the privacy constraints of federated settings. To address these limitations, we propose Fed-LSVI, the first provably efficient federated algorithm for online reinforcement learning with linear function approximation in episodic Markov decision processes. By integrating a determinant-based event-triggered synchronization with a stepwise backward update mechanism, Fed-LSVI enables agents to collaboratively learn an optimal policy by exchanging only compressed sufficient statistics. We prove that Fed-LSVI achieves a regret bound of $\widetilde{\mathcal O}(\sqrt{Md^3H^4T})$, where $d$ is the feature dimension, $H$ is the horizon length, $M$ is the number of agents, and $T$ is the number of episodes per agent, matching the best-known regret for multi-agent online reinforcement learning with linear function approximation. Moreover, by following the stringent communication and privacy constraints of the federated setting, Fed-LSVI reduces the communication cost to only logarithmic dependence on $T$, representing a significant improvement over prior methods.

stat.ML↗
arXiv2026

Curriculum-Aware Interpolate-then-Refine: Learned Physiological Time-Series Imputation under Realistic Missingness

Imputing physiological time series (arterial blood pressure, blood glucose, etc.) is essential for addressing the missingness that pervades clinical data. Yet modern imputation methods perform poorly in this domain: a recent benchmark found that simple linear interpolation outperformed every learned imputer on real-world clinical signals with realistic gaps. We show that this reflects two properties of physiological missingness that generic imputers ignore: gaps may occur when the signal is clinically extreme rather than typical, and gap lengths can easily span orders of magnitude. To this end, we introduce Curriculum-Aware Interpolate-then-Refine (CAIR), a two-stage framework for physiological time-series imputation. Our key motivation is to learn a coarse base curve and then repeatedly correct it toward physiological realism, rather than predict a gap in a single pass. Consequently, CAIR couples a bidirectional-GRU interpolator with a Transformer refiner that corrects its own estimate over three successive passes, trained jointly under a broad, signal-agnostic random-gap curriculum. We evaluate imputers stratified by gap length and missingness mechanism (MCAR, MAR, NMAR) rather than by a single average, and CAIR is the most accurate under every mechanism on continuous glucose monitoring (AI-READI) and arterial pressure in intensive care (MIMIC-III). Its margin over the strongest baseline grows with difficulty, from 9% under MCAR to 19% under value-dependent dropout, where generic learned imputers are weakest. We further show low reconstruction error alone does not recover the burden metrics clinicians act on: interpolants matching CAIR's error fail to preserve those metrics, imputers that recover them are far less accurate, and CAIR alone ranks among the best on both axes.

cs.LG↗
arXiv2026

CAST: Context- and Anomaly Structure-Conditioned Time Series Anomaly Generation

Anomalous time series play a critical role in safety-critical domains, yet they are inherently scarce, heterogeneous, and costly to obtain. Existing time series generation methods predominantly focus on synthesizing normal data, providing limited value when anomalous samples are needed. We identify two fundamental challenges in anomaly generation: (i) the scarcity of anomaly data, and (ii) the heterogeneous morphological characteristics of anomalies. To address these challenges, we propose CAST, a Context- and Anomaly Structure-conditioned Time series anomaly generation framework with principled two-stage pretraining and finetuning strategy. In pretraining stage, we leverage abundant normal time series data to learn underlying system dynamics and substantially mitigate the limited availability of anomaly data. During finetuning, CAST explicitly conditions the generator on learned anomaly structure representations, enabling it to capture heterogeneous anomaly morphologies under similar contextual conditions. Extensive experiments on multiple real-world univariate and multivariate datasets demonstrate that CAST consistently outperforms state-of-the-art anomaly generation methods in terms of both generation fidelity and downstream task utility, highlighting the effectiveness of the proposed approach.

cs.LG↗
arXiv2026

SQL-RewriteBench: A Correctness-Gated, Full-Denominator Benchmark for Statement-Level SQL Rewriting [Experiment,Analysis & Benchmark]

Statement-level SQL rewriting can improve query performance and maintainability without changing the DBMS kernel, but existing benchmarks do not evaluate rewrite methods as deployable systems. They typically focus on DBMS performance, rule regression, query equivalence, or dialect translation, while missing the full path from accepting an input query to producing an executable, result-consistent, and operationally useful rewrite. We present SQL-RewriteBench, a benchmark for statement-level SQL rewriting that applies correctness gating and full-denominator accounting. Its metric suite explicitly separates Source Acceptance, Generation Rate, Execution Coverage, Result Consistency, UnsafeRewrite Rate, and speedup distribution. It also defines SCS, a deterministic index of static SQL structure, and CGOQ, a correctness-gated optimization-quality score that gives optimization credit only after the case-specific Checker Contract is satisfied. CGOQ combines runtime improvement with structural simplification through a continuous scoring function, making it suitable for deployment-oriented rewrite assessment. As an artifact, SQL-RewriteBench provides 180 executable Benchmark Instances organized into EQUIV, PERF, ROBUST, and DIALECT pools, each packaged with SQL, schema metadata, provenance, evidence, and rewrite-opportunity documentation. Across seven representative academic and LLM-based methods, every full-benchmark CGOQ is negative. Existing methods often fail before rewriting, fail result checks, or return correct rewrites that are slower or no better than the input. These results show that deployable SQL rewrite requires broader input handling, result validation, and benefit-aware rewrite decisions.

cs.DB↗
arXiv2026

Represent, Then Generate: Multimodal-Conditioned Time-Series Generation under Irregular Missingness

Continuous physiological time series underpin modern clinical monitoring, yet many of the most informative signals are invasive, expensive, or simply unavailable for a given patient. Conditional generation offers a remedy: an absent signal can be synthesized from co-recorded signals and routine clinical variables. Existing generators, however, are built around a single conditioning modality and degrade when forced to handle the heterogeneous, irregularly missing mix of time-variant signals and static covariates seen in practice. We propose ReCoGen (Represent Conditions, then Generate), a two-stage framework that decouples multimodal condition representation from target generation. Stage I trains one masked autoencoder per modality, distilling each time-variant condition into a compact and missingness-tolerant token sequence. Stage II trains a flow-matching generator that fuses these tokens with static conditions to synthesize the target signal. Across three physiological benchmarks, including continuous glucose monitoring on AI-READI and arterial blood pressure generation on MIMIC-III and MIMIC-IV, ReCoGen attains the best downstream utility on all sixteen (dataset, task, metric) settings, surpassing six representative conditional generators; on thirteen of them its utility also reaches or exceeds the utility measured on the real signal, a reference we read as an approximate anchor rather than a ceiling. Ablations trace the gains to the conditioning path: learnable cross-attention over the frozen per-modality encoders, and a dual token-plus-AdaLN route for the static conditions. ReCoGen thus turns routinely collected signals into informative surrogates for invasive or unavailable ones, a step toward less invasive, lower-cost continuous clinical monitoring.

cs.LG↗
arXiv2026

Flatness Preserves Instruction Following in Vision-Language-Action Models

Vision-language-action (VLA) models have the potential for open-world generalization by leveraging pretrained vision-language representations, yet downstream finetuning on limited robot data often degrades these representations, leading to brittle policies that ignore language instructions in favor of visual shortcuts, a failure mode we term instruction blindness. We hypothesize that standard finetuning with limited data applies gradients to a sparse set of points, which manifests as a sharp loss landscape with high-curvature minima. We propose to address this directly through flatness-preserving optimization while finetuning on the exact same data, where learning a flatter landscape results in a model more robust to perturbations in the weight space. Specifically, we demonstrate that simply applying sharpness-aware minimization during VLA finetuning significantly improves instruction following by over 60% across multiple simulation and real-world benchmarks without additional data, architectural modification, or retraining. We further analyze the effect of selective sharpness, quantify its effects, and show that our approach is complementary to existing guidance techniques. Project page can be found at https://haochenz11.github.io/papers/flatness-vla/.

cs.RO↗
arXiv2026

Inductive Generalization for Robotic Manipulation

Understanding the generalization capabilities of visuomotor policies is essential in the development of capable robotic agents. Generalizable models learn structures that transfer across domains. However, in practice, visuomotor policies test performance by interpolation on known distributions using unstructured domain shifts (e.g. lighting, clutter, diverse objects). We argue that to measure generalization capabilities we must instead test the inductive capacity of policies on progressively harder, out-of-distribution task variants. We call this inductive generalization, drawing directly on how axis-based evaluation has revealed inherent generalization limitations in language models (e.g. sequence length, counting) arXiv:2502.00197 . We provide a reusable and formal evaluation protocol for measuring inductive generalization in any manipulation policy, and establish baselines showing that existing paradigms fail this test; e.g. SoTA Vision-Language-Action models and find that policies that appear to generalize to prior domain shifts (distractors, etc) fail inductive generalization tests. These results expose a class of learning challenges orthogonal to those addressed by data and model scaling in robot learning, yet are imperative to solve in order to realize general purpose robots.

cs.RO↗