arXiv subjects

Yang Liu

Publications and source records attributed to Yang Liu.

At least 19 recordsLinked to original sources

arXiv2026

Human Evaluation with Automatic Scores: Separating Sampling and Estimation Gains

Automatic judges offer inexpensive information about model outputs, but an evaluation team must decide how to turn that information into fewer human annotations. Scores can guide sampling, correct an estimate, or support adaptive acquisition, and these uses may capture overlapping gains. We compare their incremental value on fixed evaluation pools from three preference datasets, and 19 attributed-question-answering systems. Matched comparisons use the same scores, account for pilot labels and budget rules, and separate acquisition from estimation. Score stratification is a strong reference: after ten-bin stratification, the best fixed local linear correction offers only 1.00--5.27% further MSE reduction in the primary configurations. Unequal allocation offers larger gains in some pools, but can increase error when confident scores conceal variable human outcomes. Comparison on AttributedQA, shrinking learned quotas toward score-only quotas lowers pooled MSE for 17 of 19 systems relative to the score-only procedure, but ordinary pooled 95% intervals cover only 88.09--93.54%. The same shrinkage improves on the score-only reference in only one of eight preference configurations. Ranking experiments further show that lower individual MSE need not improve system selection. These findings support a simple starting procedure, proportional sampling within score strata followed by a stratified human mean, and identify what additional evidence is needed to justify correction or adaptation for the intended evaluation output.

cs.CL↗

arXiv2026

DART: Differentiable Dynamic Adaptive Region Tokenizer for Vision Foundation Models

The content-agnostic, fixed-grid tokenizers used by standard large-scale vision models like Vision Transformer (ViT) and Vision Mamba (Vim) represent a fundamental performance bottleneck, creating a trade-off between capturing fine-grained detail and suffering from redundant computation. To resolve this dilemma, we introduce DART, a fully differentiable Dynamic Adaptive Region Tokenizer. DART employs learnable region scores and quantile-based partitioning to create content-aware patches of varying sizes, intelligently allocating a higher token density to information-rich regions. The impact of this approach is profound: it unlocks a more intelligent scaling paradigm, where a DART-equipped DeiT-Small (22M parameters) matches the performance of a DeiT-Base (86M) with nearly double the inference speed by efficiently capturing high-resolution details in key regions. Furthermore, the principle of adaptive tokenization proves its generality with clear benefits in dense prediction and spatiotemporal video tasks. We argue that by resolving the tokenizer bottleneck at its source, adaptive tokenization is a key component for building the next generation of more efficient and capable foundation models for multimodal AI, robotics, and content generation. Code is available at https://github.com/HCPLab-SYSU/DART.

cs.CV↗

arXiv2026

Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents

Planning is central to LLM agents: before acting, an agent must decompose goals, select tools, reason over constraints, and decide when a task is infeasible. Yet existing agent evaluations often report only end-to-end success, making it difficult to determine whether failures stem from planning or execution. We introduce Agent Planning Benchmark (APB), a planning-specific diagnostic benchmark with 4,209 multimodal cases across 22 domains and five settings, covering holistic planning, feedback-conditioned step-wise planning, and robustness under extraneous tools, broken tools, and unsolvable tasks. Across 12 MLLMs, APB reveals systematic weaknesses in long-horizon planning, tool-noise robustness, calibrated refusal, and inference-time refinement. We further validate APB on 200 ToolSandbox tasks and 200 $τ^2$-bench tasks, where APB-guided refinement consistently improves plan correctness, plan grade, and downstream execution metrics across three representative models. APB thus serves as an upstream diagnostic complement to execution benchmarks. The APB benchmark and code are available in \href{https://github.com/Mikivishy/AgentPlanningBenchmark}{this URL}.

cs.CL↗

arXiv2026

GAUGE: Group-Wise View-Inconsistency Rectification for Feed-Forward 4D Tracking

Feed-forward models regress dense 3D point trajectories directly from monocular video, yet the residual after global alignment is substantial and lacks a structural explanation. Measured on dynamic query points across models and datasets, the error concentrates along the view direction, while the scale correction each motion group requires differs. The predicted displacement direction nevertheless supports reliable grouping, with a median angle far below the 90° random baseline. The systematic part of the residual is therefore a family of radial degrees of freedom per motion group, along directions 2D observations cannot constrain. We call it group-wise view inconsistency. We present GAUGE (Group-wise Adaptive Unsupervised Gauge Estimation), a training-free and model-agnostic post-hoc module. It recovers motion groups from direction consistency and spatial connectivity, then estimates a per-frame radial scale and group-level translation from 1% to 5% metric anchors, four degrees of freedom per group and frame. On dynamic query points of eight trackers, including D4RT, 4RC and SM4RT, our correction lowers endpoint error by 15.1% to 62.6% over the uncorrected predictions, while spending the same anchors on gradient fine-tuning improves the same models by only -1.1% to 15.2%. Code is publicly available at https://github.com/HCPLab-SYSU/GAUGE.

cs.CV↗

arXiv2026

Polarity--Time Interaction and Multi-Level Reliability for Event-Based Spacecraft Pose Estimation

Sparse event responses produce uneven keypoint errors whose effects on spacecraft pose depend on correspondence geometry and the reliability of successive observations. We present a reliability-aware framework connecting polarity--time localization, geometric recovery, event--CAD refinement, and trajectory optimization. A three-branch representation combines positive events, negative events, and recent-event timing through cross-branch attention and gating, followed by spatiotemporal aggregation. An ordered semantic-point head estimates relative correspondence precision for geometrically constrained pose recovery. Event-edge and CAD-projection agreement then guide local pose refinement under keypoint-geometry safeguards. At the sequence level, a ten-dimensional descriptor combines heatmap shape, reprojection consistency, and geometric conditioning to set time-aligned observation scales. On the official SPADES challenge test set, the complete system achieves a combined pose score of 0.0474, approximately 5.4\% below PASAN+IRIS. Validation ablations reduce the score from 0.0772 for base localization with uniform PnP to 0.0514 for the complete cascade; on identical single-frame observations, quality weighting reduces the score from 0.0549 with constant-weight optimization to 0.0514.

cs.AI↗

arXiv2026

Two-body strong decays of the $P_{cs}(4338)$ as a hidden-charm pentaquark state via the QCD sum rules

In this work, we study the hadronic coupling constants of the $P_{cs}(4338)$ as a $[us][dc]\bar{c}-[ds][uc]\bar{c}$ type pentaquark state with the spin-parity $J^P={\frac{1}{2}}^-$ via the three-point QCD sum rules according to rigorous quark-hadron quality. We select the optimal parametrization to subtract contaminations from the higher resonances and continuum states and obtain ideal hadronic coupling constants therefore the partial decay widths and total width $Γ(P_{cs}(4338))=10.48\pm 1.79\,\rm{MeV}$, which are consistent with the experimental data $Γ(P_{cs}(4338)) = 7.0\pm1.2\pm1.3 \mbox{ MeV}$ from the LHCb collaboration. The partial decay widths have the hierarchy $Γ(J/ψΛ)> Γ(\bar{D}_sΛ_c)> Γ(η_cΛ)$, which can be compared to the experimental data in the future to distinguish the pentaquark and molecule scenarios.

hep-ph↗

arXiv2026

GAWM: A Compact Latent World-Action Model for Multi-Task Robot Manipulation

World-action models (WAMs) incorporate the prediction of future observations into robot policy learning. However, most WAMs build on billion-parameter vision-language or video-generation backbones, which incur high training cost and inference latency. In this letter, we present GAWM (Geometry-Aware World Model), a compact multi-task WAM that predicts future observations in the latent space of a frozen DINOv3 encoder. GAWM compresses the features of each camera view into a small set of tokens. A lightweight predictor, conditioned on the task rather than on actions, forecasts these tokens at two future horizons. The forecast is supervised with the dense patch features of future frames, which requires it to encode the spatial layout of the future scene. An action decoder directly regresses a chunk of future actions from the current and predicted tokens. With fewer than 100M parameters and no robot or video pretraining, GAWM outperforms billion-parameter WAMs on RoboTwin 2.0 and performs comparably to billion-parameter VLAs on LIBERO. On a dual-arm robot, it achieves lower action-prediction error on held-out demonstrations than a fine-tuned billion-parameter VLA, with substantially lower inference latency. Ablation studies show that the latent world model substantially improves performance when training data or training time is limited. Code is available at https://github.com/gaoxiang12/ga-wm.

cs.RO↗

arXiv2026

Topological Criticality with Charge-$3e$ Fluctuations in the $\mathrm{SU}(3)$ Triangular-Lattice Hofstadter--Hubbard Model

A transition between an integer quantum Hall insulator and a chiral spin liquid can become critical without closing the single-electron gap, raising the question of which composite excitations govern the change in topological order. We investigate this question in the $\mathrm{SU}(3)$ triangular-lattice Hofstadter--Hubbard model at one particle per site and magnetic flux $π/3$ per triangle. Using infinite density matrix renormalization group calculations, we identify a weak-coupling integer quantum Hall phase and an interaction-driven $\mathrm{SU}(3)_1$ chiral spin liquid. Near the transition, both the neutral and charge-$3e$ correlation lengths increase substantially, whereas the single-electron correlation length remains short, providing evidence for a Chern--Simons--Higgs critical theory, where a gauge-invariant monopole carries the quantum numbers of a fermionic $\mathrm{SU}(3)$-singlet trion. We discuss the implications for doping the system and recent experiments on doping $ν=-2/3$ fractional quantum anomalous Hall in tMoTe$_2$.

cond-mat.str-el↗

arXiv2026

LIME: Link-based User-item Interaction Modeling with Decoupled XOR Attention for Efficient Test Time Scaling

Scaling large recommendation systems requires advancing three major frontiers: processing longer user histories, expanding candidate sets, and increasing model capacity. While promising, transformers' computational cost scales quadratically with the user sequence length and linearly with the number of candidates. This trade-off makes it prohibitively expensive to expand candidate sets or increase sequence length at inference, despite the significant performance improvements. We introduce \textbf{LIME}, a novel architecture that resolves this trade-off. Through two key innovations, LIME fundamentally reduces computational complexity. First, low-rank ``link embeddings" enable pre-computation of attention weights by decoupling user and candidate interactions, making the inference cost nearly independent of candidate set size. Second, a linear attention mechanism, \textbf{LIME-XOR}, reduces the complexity with respect to user sequence length from quadratic ($O(N^2)$) to linear ($O(N)$). Experiments on public and industrial datasets show LIME achieves near-parity with state-of-the-art transformers but with a 10$\times$ inference speedup on large candidate sets or long sequence lengths. When tested on a major recommendation platform, LIME improved user engagement while maintaining minimal inference costs with respect to candidate set size and user history length, establishing a new paradigm for efficient and expressive recommendation systems.

cs.IR↗

arXiv2026

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation

Large vision-language models (LVLMs) have emerged as a powerful paradigm for multimodal intelligence, but their growing deployment also expands the attack surface of prompt injection. Despite this growing concern, existing attacks still suffer from a critical limitation: the injected prompt for one modality only steers the model's interpretation of that singular input. Alternatively, these attacks remain multimodal but fail to achieve cross-modal prompt perturbation. To bridge this gap, we introduce a novel cross-modal prompt injection attack CrossMPI, which can steer the model's interpretation of both textual and visual inputs via image-only prompt injection. Our design is underpinned by the following key breakthroughs. First, we turn the focus of the injected prompt perturbation optimization from the visual embedding space (typically with only $10^5$ parameters) to the model hidden state space (for multimodal information integration and with $10^7$ parameters). Then, two strategies are adopted to mitigate the optimization challenges posed by the larger parameter space. To constrain the optimized model parameter space, we introduce a layer selection strategy that identifies the layers most critical to multimodal integration. Interestingly, deviating from the past experience, our analysis reveals that the optimal layers for LVLM prompt perturbation reside in the middle of the model rather than the last. To constrain the image perturbation space, we propose a new distance-decremental perturbation budget assignment strategy that allocates budgets decrementally as the pixel distance to semantic-critical regions increases. Extensive experiments across multiple LVLMs and datasets show that our method significantly outperforms baseline approaches.

cs.CR↗

arXiv2026

TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems

User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints due to fixed-dimensional vectors. As an emerging alternative for discrete user representation, LLM-generated natural-language user profiles often capture language semantics rather than sequential patterns in user behaviors. Meanwhile, Semantic ID (SID) is effective for item representation, yet existing discrete user representations remain largely confined to quantizing already-pooled user vectors, clustering historical watches, or predicting coarse topic clusters solely for candidate retrieval. We propose TokenMinds, an industrial system that extends the PLUM framework from SID-based item retrieval to generative sequential user modeling. Built on an encoder-decoder architecture adapted from pretrained LLMs, TokenMinds introduces a dual-output design: the encoder outputs a dense user embedding capturing a holistic user state, while the decoder generates discrete SID-based user tokens representing multi-faceted future interests. Grounded in item semantics, these tokens preserve distinct interests that a single pooled vector would average away. Additionally, a shared SID vocabulary across long- and short-form videos unifies cross-scenario behaviors into a single model, cutting upstream training and serving compute by 50% and 31%. Furthermore, leveraging the text vocabulary inherited from the pretrained LLM, TokenMinds interleaves textual search queries directly with watch histories to capture explicit user intent. We validate TokenMinds through offline evaluations and live A/B experiments across YouTube's primary ranking surfaces, serving billions of users asynchronously: SID-based user tokens are effective on their own, yield additive gains alongside dense embeddings, and together outperform the previous-generation, non-LLM user model in production.

cs.IR↗

arXiv2026

Learning Direct Control from Optimization for Dynamic Target Tracking

Dynamic target tracking requires a mobile robot to maintain target visibility while navigating obstacles with smooth, feasible controls. Online trajectory optimization explicitly encodes these objectives but requires repeated numerical solving, whereas waypoint-based neural policies separate geometric prediction from control execution. We introduce LECO, a framework that transfers tracking optimization into offline learning of a direct-control policy. LECO predicts control sequences and maps them to trajectories through a differentiable kinematic model, allowing trajectory-level objectives to directly guide control learning. A decaying expert-guidance curriculum initializes effective tracking behavior and progressively shifts learning toward these task objectives. At deployment, a predictive safety lock checks short-horizon obstacle clearance and invokes a classical planning and control fallback when the predicted motion is unsafe or the target prediction is invalid. Across three simulated obstacle densities, LECO reduces root-mean-square linear jerk by 14.1--31.2\% relative to the best competing method for this metric and achieves the highest tracking success rate, with per-cycle computation times of 4.25--5.63\,ms. Experiments on two robot platforms further demonstrate tracking through indoor narrow passages and outdoor forest environments. These results demonstrate that learning direct control from optimization enables smooth and robust dynamic target tracking.

cs.RO↗

arXiv2026

Agents' Last Exam

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long horizon, economically valuable, real world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 sub fields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is below 1%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP relevant impact.

cs.AI↗

arXiv2026

Inferring Nuclear Radial Parameters from Initial-State Information in Heavy-Ion Collisions Using Deep Neural Networks

The geometric structure of atomic nuclei plays an important role in shaping the initial conditions of high-energy nuclear collisions and the subsequent evolution of the quark--gluon plasma. In this work, we develop a multimodal deep-learning framework to infer the Woods--Saxon radius ($R_0$) and diffuseness parameter ($a$) from initial-state information. Using the TRENTo model for relativistic $^{238}$U+$^{238}$U collisions, we construct a dataset covering multiple combinations of $R_0$ and $a$, and perform parameter regression by combining two-dimensional entropy-density distributions with event-level scalar observables, including multiplicity and eccentricities $\varepsilon_2$--$\varepsilon_5$. The results show that the proposed framework can effectively recover the Woods--Saxon parameters from initial-state information. Joint multi-event inputs suppress statistical fluctuations and improve regression performance by enhancing the extraction of collective information. The inversion accuracy exhibits a pronounced centrality dependence: $R_0$ is best constrained in central collisions, whereas $a$ shows the strongest sensitivity in the mid-peripheral region and becomes less well constrained in ultra-central and peripheral collisions. These findings indicate that the initial-state geometry retains useful information about nuclear radial structure and provide a baseline for future studies that incorporate transport evolution and experimental final-state observables.

nucl-th↗

arXiv2026

HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience

Extending Vision-Language-Action models (VLAs) to humanoid robots requires coordinated whole-body control and diverse demonstrations that are costly to collect in real-world scenarios. Although egocentric human demonstrations provide a complementary source of task experience, differences in visual embodiment and missing robot proprioception complicate transfer to humanoid policies. To address these challenges, we introduce HuGe, a family of Humanoid Generalist VLAs pre-trained on over 2,000 hours of egocentric human and robot data. Specifically, HuGe employs three existing representative VLA architectures to predict latent motion tokens for a pretrained whole-body controller, together with hand-control signals. Based on this, we introduce a three-stage training pipeline that combines egocentric pre-training, humanoid adaptation, and downstream fine-tuning. To facilitate transfer across embodiments, we construct pseudo-proprioceptive states through simulation playback during pre-training and modify arm appearance in egocentric observations through re-rendering during downstream fine-tuning. With this pipeline, HuGe achieves the state-of-the-art on simulation benchmark HumanoidArena. Furthermore, real-world experiments on the Unitree G1 indicate that augmenting robot demonstrations with visually adapted egocentric demonstrations significantly increases success on a pick-and-drop task.

cs.RO↗

arXiv2026

Synergizing Wireless Foundation Models and LLMs: A Multi-Task Framework for MA Systems

While movable antennas (MAs) provide enhanced spatial flexibility through dynamic repositioning, they confront critical challenges in acquiring complete channel state information (CSI) and efficiently optimizing antenna positions. Encouragingly, wireless foundation models (WFMs) capture generalizable channel priors for high-quality CSI extrapolation, while large language models (LLMs) enable parameter-efficient, token-level optimization for wireless tasks. In this paper, we synergistically integrate a WFM and an LLM into a multi-task framework for MA systems. First, to address the mismatch between existing WFM pre-training and MA channel characteristics, we develop an MA-oriented ``ExtLWM'' based on the large wireless model (LWM) architecture. Second, we design a unified ExtLWM-Connector-LLM architecture that flexibly adapts to different MA configurations without structural redesign. Third, we reformulate discrete MA positioning as a sequential decision-making problem, where candidate positions are represented by numerical tokens and optimized using group relative policy optimization (GRPO) to exploit the serial generation capability of the LLM. Finally, a multi-stage training strategy is developed to maintain multi-task performance under limited training samples while mitigating catastrophic forgetting. Simulation results show that ExtLWM can produce high-quality channel embeddings while outperforming various benchmarks in CSI extrapolation. Meanwhile, the proposed LLM-based approach achieves a favorable trade-off between performance and computational complexity.

eess.SP↗

arXiv2026

AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal Transport

Flow-based Generative Models (FGMs) effectively transform noise into complex data distributions. Incorporating Optimal Transport (OT) to couple noise and data during FGM training has been shown to improve the straightness of flow trajectories, enabling more effective inference. However, existing OT-based methods estimate the OT plan using (mini-)batches of sampled noise and data points, which limits their scalability to large and high-dimensional datasets in FGMs. This paper introduces AlignFlow, a novel approach that leverages Semi-Discrete Optimal Transport (SDOT) to enhance the training of FGMs by establishing an explicit, optimal alignment between noise distribution and data points with guaranteed convergence. SDOT computes a transport map by partitioning the noise space into Laguerre cells, each mapped to a corresponding data point. During FGM training, i.i.d. noise samples are paired with data points via the SDOT map. AlignFlow scales well to large datasets and model architectures with negligible computational overhead. Experimental results show that AlignFlow improves the performance of a wide range of state-of-the-art FGM algorithms and can be integrated as a plug-and-play component. Code is available at: https://github.com/konglk1203/AlignFlow.

cs.LG↗

arXiv2026

SimSkip: StrongARM-Comparator Similarity Sensing with SAR-Skipping-Aware Training for Analog Compute-in-Memory

Analog-to-digital conversion dominates the energy and area of analog compute-in-memory (CIM) accelerators. This paper presents SimSkip, a successive-approximation-register (SAR) skipping scheme that combines a lightweight StrongARM-comparator similarity detector with SAR-skipping-aware training. When two held voltages are similar, the upper bits of the preceding code are reused to skip SAR comparisons. Detector-induced disturbance extracted from 55-nm CMOS simulations and bit-exact prefix saturation are embedded in the forward pass, and the network learns to tolerate them through quantization-aware training and knowledge distillation. On an ISAAC-based W4A4 WRN-28-10, SimSkip achieves 77.23% CIFAR-100 top-1 accuracy (mean of three seeds) versus 78.4% for the baseline, while reducing SAR comparisons by 48.2% across three hardware-modeled layers. A first-order model estimates a 27.2% net ADC energy reduction after detector overhead.

cs.AR↗