arXiv subjects

Shuang Liang

Publications and source records attributed to Shuang Liang.

At least 19 recordsLinked to original sources

arXiv2026

RobotAgentBench: Towards Open-world Robot Autonomy

Recent advances in vision-language-action (VLA) and world-action models (WAMs) have significantly improved robotic manipulation, yet deploying robots in the open world demands a higher level of autonomy beyond executing predefined tasks. Robot agents offer a promising paradigm for this transition, integrating task discovery, contextual reasoning, physical execution, and adaptive recovery into a closed interaction loop. However, existing benchmarks largely evaluate isolated capabilities, failing to capture the complexity of open-world robot autonomy. We introduce RobotAgentBench (RAB), a comprehensive benchmark for evaluating robot agents in realistic, open-world household environments. Through an agent-assisted, human-in-the-loop real-to-sim pipeline, RAB constructs 50 diverse household layouts with interactive objects and physically grounded tasks, encompassing 90 atomic tasks, 18 short-horizon tasks, 8 long-horizon tasks, and 4 open-ended scenarios. RAB provides a multi-level evaluation of robot agent capabilities: (1) task-level assessments systematically examine five complementary dimensions: task discovery, context reasoning, manipulation, failure recovery, and robustness; (2) scenario-level evaluation assesses how agents integrate these capabilities to autonomously fulfill high-level user needs. Furthermore, RAB enables systematic comparisons of standalone VLA/WAM models and diverse robot agent architectures under a unified planning-execution-verification framework. Extensive experiments reveal substantial gaps between manipulation and autonomy, demonstrate the advantages of agentic architectures and recursive self-improvement, and highlight the remaining challenges toward open-world robot autonomy.

cs.RO↗

arXiv2026

When Connectivity Misleads: Guiding Agentic Search with Contrastive Evidence Paths

Search agents can use cross-document graphs to discover sources through multi-hop connections and choose subsequent actions based on candidate rankings and relationships within a limited observation window. However, documents may rank highly because their numerous connections make them easier to reach, without necessarily providing more valuable evidence. Graph diffusion methods such as Personalized PageRank (PPR) aggregate propagation contributions from multiple sources, allowing highly connected distractor nodes to crowd the observation window. Flat node scores also obscure cross-document evidence trails, limiting continued exploration. We propose Contrastive Evidence Paths (CEP), which scores candidates by their strongest individual paths on a query-conditioned document graph and calibrates these scores against the same graph's background visitation distribution to mitigate structural bias. CEP ranks candidates by the calibrated scores and retains the corresponding source paths. Building on CEP, we develop Structured Corpus Interaction (SCI), which organizes candidates and their connecting paths into a structured Map, enabling agents to verify source documents and pursue missing information through expansion from anchor documents. Experiments on BrowseComp-Plus and TREC-COVID show that SCI achieves state-of-the-art answer accuracy and nDCG@10 with the lowest generation cost. Compared with the strongest baselines by task performance, maximum reductions in tool calls and total generation costs exceed 50% and 40%, respectively. Further analysis confirms that SCI with CEP suppresses ranking inflation induced by structural connections and improves gold recall and exploration efficiency.

cs.IR↗

arXiv2026

SDPose: Exploiting Diffusion Priors for Out-of-Domain and Robust Pose Estimation

Pre-trained diffusion models provide rich latent features across U-Net levels and are emerging as powerful vision backbones. While prior works such as Marigold and Lotus repurpose diffusion priors for dense geometric perception tasks such as depth and surface normal estimation, their potential for cross-domain human pose estimation remains largely unexplored. Through a systematic analysis of latent features from different upsampling levels of the Stable Diffusion U-Net, we identify the levels that deliver the strongest robustness and cross-domain generalization for pose estimation. Building on these findings, we propose SDPose, which (i) extracts U-Net features from the selected upsampling blocks, (ii) fuses them with a lightweight feature aggregation module to form a robust representation, and (iii) jointly optimizes keypoint heatmap supervision with an auxiliary latent reconstruction loss to regularize training and preserve the pre-trained generative prior. To evaluate cross-domain generalization and robustness, we construct COCO-OOD, a COCO-based benchmark with four subsets: three style-transferred splits to assess domain shift and one corruption split (noise, weather, digital artifacts, and blur) to test robustness. With data-efficient fine-tuning, SDPose achieves performance comparable to Sapiens on COCO, and establishes the best zero-shot performance on cross-domain datasets.

cs.CV↗

arXiv2026

Redshift Assessment Infrastructure Layers (RAIL): Rubin-era photometric redshift stress-testing and at-scale production

Virtually all extragalactic use cases of the Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) require the use of galaxy redshift information, yet the vast majority of its sample of tens of billions of galaxies will lack high-fidelity spectroscopic measurements thereof, instead relying on photometric redshifts (photo-$z$) subject to systematic imprecision and inaccuracy best encapsulated by photo-$z$ probability density functions (PDFs). We present the version 1 release of Redshift Assessment Infrastructure Layers (RAIL), an open source Python library for at-scale probabilistic photo-$z$ estimation, initiated by the LSST Dark Energy Science Collaboration (DESC) with contributions from the LSST Interdisciplinary Network for Collaboration and Computing (LINCC) Frameworks team. RAIL's three subpackages provide modular tools for end-to-end stress-testing, including a forward modeling suite to generate realistically complex photometry, a unified API for estimating per-galaxy and ensemble redshift PDFs by an extensible set of algorithms, and built-in metrics of both photo-$z$ PDFs and point estimates. RAIL serves as a flexible toolkit enabling the derivation and optimization of photo-$z$ data products at scale for a variety of science goals and is not specific to LSST data. We thus describe to the extragalactic science community, including and beyond Rubin the design and functionality of the RAIL software library so that any researcher may have access to its wide array of photo-$z$ characterization and assessment tools.

astro-ph.IM↗

arXiv2026

Microscopic Theory of Drag in a Bose Condensate Interacting with a Moving Reservoir

We derive a microscopic theory of drag for a Bose-Einstein condensate interacting with a moving reservoir. Starting from interactions between a condensate and a drifting fermionic bath, we integrate out the bath degrees of freedom within the Born--Markov approximation to obtain an effective Gross--Pitaevskii equation with a drag potential. From this potential we derive an effective drag force and obtain a closed expression for the drag coefficient, determined by the reservoir density fluctuations and the condensate density profile. As an application, we simulate the drag for an exciton--polariton condensate interacting with a drifting electron gas.

cond-mat.quant-gas↗

arXiv2026

MetaCascade: End-to-End Attacks on Agent Skills via Metadata-Only Poisoning

As a key extension mechanism for agent systems, Agent Skills package specialized capabilities for reuse by LLM agents. An agent first retrieves candidate skills based on skill documentation and then relies on their metadata to make the final selection. As third-party skills proliferate on insufficiently vetted open registry platforms, the security risks posed by malicious skills become increasingly prominent, but existing attack research still focuses primarily on the potential harm caused after their execution. The limited related studies typically examine skill retrieval or selection in isolation and have yet to cover a complete end-to-end attack chain. To address this research gap, we find an end-to-end attack surface arising from the process-wide influence of metadata. Based on this finding, we propose MetaCascade, an end-to-end metadata-only poisoning framework. MetaCascade first generates diverse malicious skill candidates through multi-view semantic expansion, then uses tasks and black-box competition feedback to analyze the competitive relationships among malicious candidate skills and iteratively optimize malicious metadata, thereby improving the target skill's end-to-end attack effectiveness. Under a unified evaluation setting spanning four datasets and two agents, Hermes and OpenClaw, MetaCascade achieves state-of-the-art attack performance, with its average attack success rate (ASR) and its average ASR under four defense settings exceeding the strongest baselines under the corresponding settings by 35.53 and 34.65 percentage points, respectively. Our code is provided in the supplementary material.

cs.CR↗

arXiv2026

DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression

Long-context large language models (LLMs) have demonstrated strong capabilities across a wide range of tasks, but the growing KV cache introduces substantial memory and inference overhead. Existing one-shot KV cache compression methods typically commit to irreversible eviction immediately after prefill, before any signal from actual generation becomes available. Our quantitative analysis shows that early queries from the actual generation stage provide attention signals that are more consistent with subsequent decode attention, with the largest single-step gain occurring at the prefill-decode boundary. Based on this observation, we propose DeferKV, which moves the eviction decision from the end of prefill to the first real decoding step and temporally combines prompt-side and decode-side observations, thereby better aligning KV importance estimation with subsequent generation requirements. DeferKV requires no additional training, draft model, or future-query prediction module, making it simple and easy to deploy. Experiments on LongBench, RULER, and Needle-in-a-Haystack demonstrate that DeferKV consistently improves model performance under KV cache compression while maintaining low inference latency.

cs.CL↗

arXiv2026

Association profile conditioning in a set-temporal transformer for cross-session intracortical motor decoding

Intracortical motor decoders degrade across sessions because the set of recorded units changes and persisting units can alter how their firing relates to behavior. Most existing methods update network weights on each new session or rely on unlabeled activity, which does not directly reveal such changes. We present APST, an Association Profile-conditioned Set-Temporal transformer that adapts to new sessions with all network weights frozen. From a few labeled calibration trials, APST summarizes how each unit's firing relates to behavior in a four-dimensional association profile computed in closed form. The profiles condition a set-attention encoder that accepts any number and order of units, followed by a causal transformer for streaming decoding. On held-out DANDI688 sessions from two monkeys, APST reaches velocity $R^2$ of $0.78$ and $0.81$, versus $0.40$ and $0.58$ for a variant that uses neural activity alone, and matches or exceeds an RNN fine-tuned on the same trials. On FALCON private held-out evaluation, it attains $R^2$ of $0.65$, $0.42$, and $0.44$ on M1, M2, and H1.

q-bio.NC↗

arXiv2026

SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations

Given a target dataset, such as faces with eyeglasses, and a background dataset, such as faces without, contrastive analysis separates \textit{salient} factors specific to the target from \textit{common} content shared by both. We aim for salient representations that capture target-specific detail in each image, such as the shape, color, and position of the glasses, so that they reveal subtypes without subtype labels and guide the generation of new examples of a discovered subtype, even one with no name or text description. We introduce SAGE, which learns both factors directly in the high-dimensional spatial latent of a frozen representation autoencoder and conditions a diffusion transformer on the learned salient representation of a reference image. On Digits-ImageNet and FFHQ eyeglasses, SAGE combines high-fidelity \textit{reconstruction} (rFID below $2$) with unsupervised \textit{subtype discovery}, recovering the digits better than baselines (probe accuracy $0.950$ vs.\ at most $0.281$) and revealing eyewear types, finer sunglasses styles, and mislabeled images; salient-conditioned \textit{generation} raises Digits-ImageNet subtype accuracy over the unfactorized latent ($90.5\%$ vs.\ $27.7\%$) and diversity on both datasets. On retinal OCT, SAGE's salient space separates three diseases using only normal/disease labels.

cs.CV↗

arXiv2026

Beyond Skill Evolution: Self-Evolving Context Management Policies for Long-Horizon Agent Harnesses

Harness evolution improves LLM agents by learning from execution trajectories, but existing experience- and skill-based methods are less effective on long-horizon tasks. As interactions grow, useful evidence can be buried by redundant or outdated context, making context management itself a key bottleneck. We introduce ContextEvo, a framework that learns a context policy from long-horizon trajectories. ContextEvo reconstructs the model-visible context at key decision points, identifies context-related failures, and applies targeted policy updates. Starting from the open-source Pi-agent harness, ContextEvo improves performance across three long-horizon task benchmarks, achieving results comparable to or better than several prominent agent harnesses, including Codex, OpenCode, and OpenClaw. Additional analyses show that fixed or locally evolved context strategies can fall short under long-horizon information pressure, while our methods adapt to the information demands of each environment.

cs.AI↗

arXiv2026

FlowAct-R2: Beyond Talking Avatar via Streaming Multimodal References and Proactive Agent Planning

We present FlowAct-R2, a framework for interactive humanoid video generation that combines continuous multimodal control with proactive agent planning. Our method consists of two coupled components. First, a Streaming Multimodal Reference Diffusion Transformer adapts the pretrained Seedance 2.0 Mini reference-to-video backbone to accept rolling action prompts, streaming audio, and dynamically updated image, audio, and video references. Video-driven rotary positional embeddings align reference chunks with the generation timeline, while reference-plus-image conditioning and partially noised historical motion frames preserve appearance and avoid accumulated drift. Second, a Proactive Interaction Agent separates pre-online planning from online scheduling and response: it prepares a persona, a long-horizon agenda, and reusable multimodal skills in advance, then autonomously schedules behaviors, responds to audience input, and handles interruptions during a live session. FlowAct-R2 supports real-time 720p generation and hour-scale streaming across entertainment streaming, live shopping, video chatting, and live vlogging.

cs.CV↗

arXiv2026

Causally Debiased Latent Action Model for Embodied Action-Conditioned World Models

Action-conditioned world models (ACWMs) aim to simulate future observations conditioned on embodied actions. However, learning controllable ACWMs requires large-scale action-labeled data, which remains costly to collect. Latent action models (LAMs) mitigate this bottleneck by inferring latent actions from videos without executable action labels, but existing LAMs are typically trained with reconstruction-only objectives and therefore entangle action-relevant dynamics with action-irrelevant visual confounders. With such objectives, LAM favors visual context over action dynamics, therefore downstream ACWMs exhibit residual motion under zero actions and fail to reproduce supplied dynamics. We propose CD-LAM, a causally debiased framework for LAM-based ACWMs. CD-LAM introduces three debiasing objectives: embodiment-centric reconstruction, action-centric contrastive learning, and latent space calibration, which together encourage embodiment-focused, action-aware, and well-calibrated representations. CD-LAM reduces action-following error by up to 42% and 35% when conditioned on latent and robot actions, while improving fidelity, and matching DreamDojo reference with over 12$\times$ fewer adaptation updates. CD-LAM also adapts LTX-2.3-22B into an ACWM with competitive quality using only 3.2% of DreamDojo-14B's sample exposures. On X-VLA, pretraining with CD-LAM instead of baseline LAM consistently improves success rates by up to 5 percent point across LIBERO, LIBERO-Plus, and RoboTwin C2R.

cs.CV↗

arXiv2026

SGA: Uncertainty Quantification for Multi-Step Forecasting in Time Series Foundation Models

The recent emergence of Time Series Foundation Models (TSFMs) has significantly advanced multi-step forecasting performance, enabling accurate predictions over extended future horizons. However, existing TSFMs often suffer from significantly inherent uncertainty, which typically manifests as derived forecast branches emerging at each time step and spreading to subsequent steps; different forecast branches often exhibit varying forecasting performance, thereby undermining the credibility of TSFM forecasts. In this paper, we propose the Slicing-Graphing-Alignment (SGA) method to quantify the uncertainty of multi-step TSFM forecasts. The proposed SGA first characterizes the topology of all potential forecast branches using a directed acyclic graph, such that the graph complexity bounds the uncertainty of multi-step forecasts, and then precisely measures the graph complexity by integrating both topological information and TSFM-inherent stochasticity. Experimental results conducted on 11 TSFMs and 27 datasets demonstrate that (i) SGA achieves the best performance when ranking predictive errors with uncertainty estimates; (ii) SGA works with a more extensive and more precise sampling coverage than those of existing UQ methods, deriving a quantification mechanism fundamentally different from those of established ones; and (iii) larger model scales of TSFMs correlate with lower uncertainty estimates of multi-step forecasts, suggesting another empirical scaling law for uncertainty quantification of multi-step TSFM forecasts.

cs.LG↗

arXiv2026

HyQDB: LLM-Assisted Debugging for Hybrid Quantum Workflows

Hybrid quantum program failures frequently occur silently, yet existing debugging tools provide limited support for detecting and repairing them. These faults dominate the failures reported by domain experts, yet existing tools evaluate on public data that under-represents this failure mode. Our key insight is that faults divide into two classes that require different strategies: mechanical faults, which allow deterministic analysis, and conceptual faults, which require reconstructing the program's intent. To address this challenge, we present HyQDB, a tiered agent that injects deterministic hardware, physics and optimization evidence into the LLM repair process. When no evidence is detected, the agent treats this silence as a signal to escalate to a second intent-reconstruction tier, that infers the program's behaviour and reconciles it with the implementation. To evaluate HyQDB, we introduce QFaultBench, a benchmark built from an expert-derived fault taxonomy that represents the true failure modes of hybrid programs. On a held-out set of human-authored programs, HyQDB raises repair success over a standard LLM from 45% to 75%. We show that the escalation gate is crucial, giving a 20% improvement in mechanical fault repair accuracy.

cs.SE↗

arXiv2026

CausalWM: Causal Chain-of-Thought Reasoning for Embodied World Model

Embodied world models learn to predict future physical dynamics from visual observations and control signals, where physical knowledge is implicitly entangled within latent representations. We introduce CausalWM, a 16B embodied world model that performs explicit causal chain-of-thought reasoning before future video prediction. CausalWM organizes useful variables into a reasoning trajectory, allowing the model to progressively capture causal dependencies underlying physical evolution. To train CausalWM, we collect 31K hours embodied data and develop a three-stage paradigm consisting of large-scale video pre-training, causal CoT mid-training, and multi-objective RL post-training. Despite using only a limited set of supervised CoT variables, CausalWM exhibits emergent in-context learning capabilities, enabling contextual visual feature guidance and efficient few-step generation. CausalWM achieves state-of-the-art performance across language-conditioned, action-conditioned, single-view and multi-view benchmarks, including Top-1 performance on TriWorldBench leaderboard.

cs.CV↗

arXiv2026

Model-Free Current Control of Permanent Magnet Synchronous Motors via ESO-Based Disturbance Feedforward and Data-Driven H-infinity Residual Feedback

This paper proposes a model-free current control method for permanent magnet synchronous motors (PMSMs) based on disturbance feedforward and residual feedback. An ultra-local current model incorporates motor dynamics, parameter uncertainties, cross-coupling effects, and other nonideal factors into generalized lumped disturbances. An extended state observer (ESO) estimates these lumped disturbances and compensates for them through feedforward action, transforming the original PMSM current-control problem into regulation of a simplified post-compensation residual system. A state-feedback H-infinity controller for the residual system is then learned directly from operating data using off-policy integral reinforcement learning. Owing to the simplified residual dynamics, the value function and control policies are parameterized in quadratic and linear forms, reducing the learning problem to low-dimensional parameter estimation without neural-network approximation. The proposed method requires neither prior knowledge nor online identification of PMSM electrical parameters: input-gain mismatch is incorporated into the ESO-estimated lumped dynamics, while the residual-feedback policy is obtained from operating data. Comparative simulations against deadbeat predictive current control, model-based H-infinity control, and model-free predictive current control show fast current tracking, low current distortion, and strong robustness to large parameter variations. With the learned H-infinity policy fixed and without retraining or retuning, nearly unchanged control performance is maintained when stator resistance, stator inductance, and permanent-magnet flux linkage are simultaneously varied to 20% and 200% of their nominal values.

eess.SY↗

arXiv2026

GRUET: Quantifying Uncertainty of Agentic Reasoning-and-Acting Processes

Agents have attracted considerably increasing attention due to the power of executing both Reasoning and Acting (ReAct) in open and dynamic environments. The ReAct process typically exhibits a multi-turn trajectory in which one drives Large Language Models (LLMs) to generate both reasoning chains and task-specific actions in an interleaved manner. However, agents often suffer from significant uncertainty, where identical tasks yield divergent trajectories; trajectories with higher uncertainty often produce incomprehensible behaviors, severely undermining agent credibility. This work conjectures that such trajectory-level uncertainty frequently stems from cumulative turn-level reasoning uncertainty induced by LLMs; the latter often exhibits a collection of branches of divergent reasoning chains and their resulting actions. Built upon this, we present the Graph-based Reasoning UncErtainty in Trajectories (GRUET) method for the uncertainty quantification of ReAct, comprising turn-level reasoning uncertainty quantification and trajectory-level uncertainty aggregation; the former precisely quantifies reasoning uncertainty via modeling the reasoning space spanned by potential reasoning branches as a graph and then approximating the reasoning space complexity with graph complexity, while the latter employs simple aggregation strategies for quantifying the overall trajectory credibility. Empirical evaluations across nine LLMs and five benchmarks validate the effectiveness of our proposed GRUET in terms of selective generation performance, measured by AUROC, AUPRC, and AUARC.

cs.AI↗

arXiv2026

Controlled Switching of Bose-Einstein Condensation in a Mixture of Two Species of Polaritons

We report temperature-dependent switching between lower and upper polariton condensation in a GaAs/AlGaAs microcavity when both of these species have comparable populations in a mixture. Using angle-resolved photoluminescence, we observe that at low temperatures, condensation occurs in the lower polariton branch, while at elevated temperatures, the upper polariton branch can become favored. At an intermediate temperature, we observe instability in the condensate formation, characterized by metastable correlations of the fluctuations in intensity and linewidth of the lower and upper polariton branches.

cond-mat.quant-gas↗