Search arXiv⌕ Search

arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 91 records · Page 5Linked to original sources
arXiv2026

ReDiffNet: Differential RGB-Infrared Learning for Low-Light UAV Oriented Vehicle Detection

Low-light UAV-based RGB-infrared oriented small-vehicle detection is important for nighttime traffic monitoring, emergency response, and urban inspection. Illumination variations, headlight glare, local shadows, and thermal-response degradation cause spatially varying modality reliability, while the small visual extent of vehicles further weakens boundaries, orientation cues, and thermal responses. Accordingly, selecting trustworthy observations based on local modality reliability while further exploiting complementary discriminative information in regions with ambiguous modality preference is key to constructing effective multimodal representations. Based on this insight, we propose ReDiffNet, a reliability-conditioned differential representation network in which modality reliability guides both evidence selection and complementary recovery. Specifically, degradation-aware reliability learning estimates relative spatial reliability, uncertainty-guided differential recovery exploits cross-modal differences to recover complementary cues in ambiguous regions, and reliability-conditioned reconstruction integrates retained and recovered evidence into a unified representation. ReDiffNet achieves 85.3% and 73.9% mAP50 on DroneVehicle and VEDAI, respectively, supporting its effectiveness.

cs.LG↗
arXiv2026

RubricArmor: Adversarial Evolution Improves LLM-Based Rubric Generation

Rubric-based reinforcement learning (RL) provides interpretable rewards for aligning large language models (LLMs) by evaluating responses against query-specific evaluation criteria. To construct rubrics at scale, a straightforward approach to LLM-based rubric generation is to prompt an LLM to generate a rubric directly from the query. However, rubrics directly generated by LLMs are vulnerable to reward hacking, since omitted or underspecified criteria allow the policy to obtain high rubric rewards with low-quality responses. Existing LLM-based rubric generation methods improve the granularity and coverage of the generated criteria but do not proactively guard against reward hacking. To address this limitation, we propose RubricArmor, an adversarial framework that exposes and mitigates potential reward hacking at the rubric generation stage before it occurs in subsequent RL. Specifically, RubricArmor performs adversarial evolution, in which an attack step and a repair step alternate over multiple rounds. The attack step simulates the reward hacking of the policy by constructing adversarial responses that satisfy the current rubric but fail to properly complete the task. The repair step then revises the rubric to detect the response defects exposed by the attack step while preserving other valid criteria. Extensive experiments demonstrate that RubricArmor outperforms competitive rubric generation baselines and translates into more effective downstream rubric-based RL.

cs.CL↗
arXiv2026

When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning

Multi-agent debate can improve reasoning, yet often fails to beat simple majority voting. We argue that successful debate requires two distinct mechanisms: proposal supply must surface a correct answer, and readout must identify that answer when voting misses it. We formalize the first requirement through recoverable headroom, which measures cases where a correct proposal is available but the majority answer is wrong. For the second, we develop Latent Verification Debate (LVD), an accounting model in which candidate proposals receive answer-specific verification evidence before final generation. Controlled fixed-proposal interventions estimate this latent effect in equivalent peer-support units and show that correct evidence changes answer probabilities and generated decisions while proposal supply remains fixed. To improve proposal supply, we construct societies from neural-thicket agents using labeled and label-free coverage objectives. Across two backbones and matched-budget reasoning benchmarks, coverage-selected societies increase complementary proposal supply and improve aggregate accuracy in repeated stochastic evaluations. Round-level controls further show that interaction provides gains beyond applying the same finalizer directly to the initial proposals. These results identify proposal coverage and truth-sensitive evidence use as complementary conditions for debate to outperform voting. Code is available at https://github.com/Wang-ML-Lab/when-debate-helps.

cs.AI↗
arXiv2026

Micromagnet engineering for enhanced addressability of donor-cluster arrays in silicon

Phosphorus donors in silicon are one of the promising platforms for fault-tolerant quantum computing, owing to their long coherence times and compatibility with complementary metal-oxide-semiconductor (CMOS) technology. However, a key bottleneck for scaling this platform lies in the independent addressability of individual spin qubits. Here, we present a scalable quantum processor architecture that integrates scanning tunneling microscope (STM)-defined phosphorus donor-cluster arrays with on-chip micromagnets. By generating magnetic field gradients, the micromagnets enable a broader addressable frequency range compared to the addressing scheme based solely on variations in hyperfine (HF) interactions, which arise from the randomness of intra-cluster configurations. Through micromagnetic simulations to optimize micromagnet geometry, we demonstrate that these structures are compatible with customized array designs, facilitating the integration of over 120 atomic spin qubits and enabling frequency multiplexing with a single microwave antenna, which greatly reduces the overhead of fan-out addressing lines. This design is further validated via magnetic measurements, which generally align with our micromagnetic simulations. These results establish a critical foundation for the development of scalable silicon quantum computing with atomic qubits.

cond-mat.mes-hall↗
arXiv2026

TandemQEC: Joint Provisioning of Streaming Quantum Error Correction in Tightly-Integrated Quantum-Classical Systems

Fault-tolerant quantum applications require timely classical decoding and feedback. Component benchmarks leave open how contention across processors, links, and finite buffers affects application progress. We propose TandemQEC, a system-level simulator connecting applications, code-specific quantum error correction schedules, and physical modalities. It models dependencies, resource availability, and buffer occupancy to explain joint provisioning decisions. We validate TandemQEC using analytical and CUDA-Q Logical references and measured pipelines. Across 960 repeated GPU/CPU runs using CUDA-Q Realtime, median absolute relative errors are 1.06% for median latency and 1.74% for 95th-percentile latency. Separate CPU-window validation covers PyMatching and BP-OSD across five code families. Studies span superconducting, trapped-ion, and neutral-atom modalities. At 32 concurrent jobs, increasing decoder capacity and bandwidth by 8x together achieves a 4.17x speedup, while either upgrade alone reduces runtime by at most 2.1%. 4x faster syndrome extraction even raises runtime under fixedduration protection due to generating more classical work. Joint upgrades recover reference performance. These findings show why component improvements require balanced provisioning to benefit applications. TandemQEC identifies useful resource combinations before complete systems are available.

quant-ph↗
arXiv2026

TimelyDAgger: Timing-Aware Expert Querying for VLA Policy Improvement

DAgger improves robot policies by aggregating expert supervision from states visited during policy execution. Robot-gated DAgger automates expert queries, allowing the robot to decide when to request expert takeover. While existing gates emphasize detecting the need for assistance, takeover timing also shapes the content of these demonstrations and their value for policy learning. We propose TimelyDAgger, combining Bridge-PCA monitoring of internal vision-language-action (VLA) features with Feedback-guided Threshold Adaptation based on expert behavior to improve takeover timing. We introduce an evaluation framework linking failure detection, takeover timing, and policy improvement, including Target-Aligned Supervision Ratio (TASR) for assessing supervision quality without retraining. Experiments show that takeover timing affects policy learning, with TimelyDAgger achieving competitive failure detection and higher post-training success in most evaluated settings under matched expert-action budgets. Project website: https://seen-e.github.io/TimelyDagger/.

cs.RO↗
arXiv2026

AvoKV-E: Payload-Aware KV Cache Eviction for Long Reasoning

Long-output reasoning shifts the KV-cache bottleneck from the fixed prompt to the generated trace. Existing reasoning-cache eviction methods largely treat cached entries as routing objects, estimating whether an old key will still be read, will recur, or can be replaced. This routing-only view overlooks two effects: low-attention entries can carry large value payloads whose removal changes future predictions, and newly generated states can appear stale before later queries have had a chance to read them. We introduce AvoKV-E, a training-free eviction policy that first delays eligibility for recent states and then ranks eligible entries using candidate-normalized read pressure, key redundancy, and value-payload potential. According to empirical evaluation across different models and datasets, AvoKV-E matches or exceeds redundancy-aware, recurrence-based, and thought-adaptive eviction baselines at matched active-KV budgets, with its largest gains in the tightest-cache regime. Component and counterfactual analyses further connect these gains to delayed observation, payload-aware scoring, redundancy, and scale-robust normalization. Together, the results show that long-reasoning KV eviction should preserve not only keys that are likely to be read, but also the value payloads that sustain the reasoning trajectory.

cs.LG↗
arXiv2026

LatentQuant: Preserving the Policy-Facing Latent Contract under NVFP4 VAE Quantization

Recent world action models (WAMs) reuse pretrained video VAEs whose encoder latents directly condition downstream action policies. Quantization must therefore preserve not only reconstruction fidelity but also the policy-facing latent contract expected by the frozen policy. Direct NVFP4 leaves W4A4 quantization error uncompensated, whereas joint quantization-aware training (QAT) can recover reconstruction by moving this representation. On Wan2.1, joint QAT nearly matches FP32 VBench-7 (0.7403 versus 0.7409), yet LIBERO success collapses from 95.5% to 10.5%. Controlled decoder-only experiments show that activation quantize-dequantize operations alter the reconstruction signal and decoder Jacobian, redirecting the gradient returned to the encoder and inducing persistent latent drift. Based on this mechanism, we introduce LatentQuant, a two-stage NVFP4 QAT framework that first aligns the quantized encoder with its high-precision counterpart, then freezes it while adapting the decoder. Across Wan2.1 and Wan2.2, LatentQuant preserves near-baseline control and high reconstruction quality, achieving 95.75% success on LIBERO and 68.8% on RoboTwin. On NVIDIA B300 GPUs, NVFP4 execution achieves 1.17x-1.26x end-to-end VAE speedups over BF16 cuDNN.

cs.AI↗
arXiv2026

Separating Expert Retention from Autonomous Source Inference in Raw-ECG-Replay-Free Continual ECG Deployment

In multi-source ECG deployment, new sources may arrive when earlier raw ECGs cannot be retained or replayed. Isolating source-specific classifiers on a frozen backbone prevents parameter interference, but source-unknown inference still requires selecting an appropriate expert. We study this distinction with IRFE-ECG, a controlled continual-deployment framework built on frozen 1024-dimensional ECGFounder features. Each arriving source adds an isolated Balanced-Softmax linear expert, while a lightweight router is re-fitted using retained frozen training features and source labels from previously observed sources. Rather than proposing a new routing architecture, the main contribution is to separate preserved expert performance from autonomous source inference and quantify the resulting deployment gap. Across CPSC, PTB-XL, Georgia, and Chapman-Shaoxing, source-aware expert selection reaches $0.7915 \pm 0.0036$ Macro-F1, close to a matched offline independent-head reference at $0.7885 \pm 0.0009$. Without source IDs, an MLP router reaches $0.7756 \pm 0.0027$, while top-2 margin fusion reaches $0.7782 \pm 0.0022$. The top-2 improvement is small (+0.0026) and not statistically significant under paired bootstrap. Across three domain orders, the top-2-to-oracle gap remains 0.0111-0.0133, indicating a persistent source-inference gap within this protocol. The results are record-level because reliable patient identifiers were unavailable. The method replays no raw ECGs, but it retains frozen feature vectors for router updates and is therefore raw-ECG-replay-free rather than memory-free. Code is publicly available at https://github.com/yufanlu221/IRFE-ECG.

cs.AI↗
arXiv2026

GIFTBench: Diagnosing Generalization in Image Forgery Localization and Informing Model Design

Reliable evaluation of image forgery localization (IFL) requires assessing models under diverse distribution changes, yet existing benchmarks often cover limited manipulation conditions or entangle multiple factors in cross-dataset evaluation. Consequently, aggregate performance provides an incomplete view of localization generalization. We introduce GIFTBench, a multi-axis benchmark of 115,013 manipulated images with pixel-level annotations spanning manipulation source, semantic target, editing operation, and composition complexity. GIFTBench supports axis-specific transfer analysis and evaluation on twelve external datasets. Its diagnostic studies reveal asymmetric cross-source transfer, recall-dominated failures, and heterogeneous degradation across semantic, operational, and compositional changes. Beyond diagnosis, the scale and diversity of GIFTBench provide a substantially broader training distribution than conventional IFL datasets. Training representative localizers on GIFTBench consistently improves their aggregate transfer to external datasets, showing that the benchmark serves not only as an evaluation tool but also as an effective training resource for cross-domain localization. Guided by the diagnostic findings, we further develop ForenScope, a detection and localization framework combining classification-adapted representations with multi-depth, multi-scale spatial features, learned layer fusion, and selective coarse-scale conditioning. Experiments show improved cross-dataset localization while retaining image-level detection capability. The GIFTBench dataset showcase page is available at https://giftbench-preview.doudoudouya337.chatgpt.site.

cs.CV↗
arXiv2026

Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks

Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows the context, self-correction diverges, tool demonstrations loop, and tasks are silently abandoned. We present evidence, from a controlled single-machine comparison and one third-party benchmark, that a substantial share of these failures is attributable to the harness rather than the model. We introduce Mingbird, a local-first agent harness for Windows and Ollama whose ten mechanisms compensate point-by-point for small-model failure forms, three of them representative: a byte-level net-zero prefill budget, a finish gate that re-reads the task before accepting completion, and signature-level loop detection. On LRAB, a controlled comparison holding machine, models, budgets, and scoring fixed (4 harnesses $\times$ 4 open models (2B-35B) $\times$ 18 real tasks, deterministic artifact scoring), Mingbird reaches 0.886 overall against 0.631 (goose), 0.479 (opencode), and 0.405 (agent-mini), with all 288 cells published; on $τ^2$-bench (278 tasks, three arms, one protocol) it totals 0.856 against 0.791 and 0.737; and a frontier-model probe on the same 18 tasks spans 0.997 to 0.478 across harnesses, with well-formed scaffolds staying within 0.072 of each other. A leave-one-mechanism-out ablation is reported as directional only: same-night replications of the same arm move its mean by up to 0.069, the size of every nominal single-trial delta, and the one batch-matched comparison (full mechanism stack versus text re-read alone) gives the executable completion guards a paired +0.10 across three replications. The evidence carries stated limits: a self-built benchmark, a single machine, and single-trial scoring.

cs.AI↗
arXiv2026

UNIQ: Communication-Efficient Distributed Quantum Computing via Unified Nonlinear Integer Programming

Distributed quantum computing (DQC) is widely regarded as a promising approach to overcome quantum hardware limitations. A major challenge in DQC lies in reducing the communication cost introduced by remote CNOT gates, which are significantly slower and more resource-consuming than local operations. Existing DQC approaches treat the three essential components (qubit allocation, entanglement management, and network scheduling) as independent stages, optimizing each in isolation. However, we observe that these components are inherently interdependent, and therefore adopting a unified optimization strategy can be more efficient to achieve the global optimal solutions. Consequently, we propose UNIQ, a novel DQC optimization framework that integrates all three components into a non-linear integer programming (NIP) model. UNIQ aims to reduce the circuit runtime by maximizing parallel Einstein-Podolsky-Rosen (EPR) pair generation through the use of idle communication qubits, while simultaneously minimizing the communication cost of remote gates. To solve this NP-hard formulated problem, we adopt two key strategies: a greedy algorithm for efficiently mapping logical qubits to different QPUs, and a JIT (Just-In-Time) approach that builds EPR pairs in parallel within each time slot. Extensive simulation results demonstrate that our approach is widely applicable to diverse quantum circuits and QPU topologies, while substantially reducing communication cost and runtime over existing methods.

quant-ph↗
arXiv2026

MoEless: Efficient MoE LLM Serving with Serverless Experts

Large Language Models (LLMs) increasingly adopt Mixture-of-Experts (MoE) architectures to scale efficiently under stringent resource constraints. However, MoE's sparse activation causes severe expert load imbalance, where a few experts become stragglers while others remain underutilized, leading to inflated inference latency and cost. Existing solutions assume static, serverful model deployments, limiting expert elasticity and often incurring costly expert swapping or degraded output quality. We present MoEless, an efficient serverless MoE serving framework that mitigates expert load imbalance via elastic expert execution. MoEless leverages lightweight, layer-aware predictors to estimate incoming expert load distributions and proactively identify stragglers. We design optimized scaling and placement strategies to improve function locality, GPU utilization, and cross-expert load balance. MoEless is prototyped on top of Megatron-LM and deployed on an eight-GPU testbed. Experiments with open-source MoE models and real-world workloads show that MoEless reduces inference latency by 43% and inference cost by 84% compared to state-of-the-art solutions.

cs.DC↗
arXiv2026

HELIX: Purified and Unified - Rethinking Feature Interaction and Sequence Modeling for Large-Scale Recommendation

Industrial recommendation ranking models typically scale along two modeling axes: feature interaction over heterogeneous user, item, context, and cross features, and sequence modeling over long, informative, and multi-type user behavior histories. We find that scaling either capability in isolation is insufficient, as each exhibits a limited scaling ceiling and a suboptimal scaling-law slope. We conjecture that achieving a more favorable scaling-law slope requires jointly scaling both axes. To support this, we present HELIX, a purified and unified architecture for large-scale recommendation. HELIX interleaves sequence retrieval and feature interaction while enforcing one-way information flow from reusable sequence states to candidate-conditioned mix-tokens. This design preserves cross-depth communication between the two modeling axes while keeping user-side sequence computation amortizable, enabling flexible and asymmetric scaling of sequence modeling and feature interaction. Deployed in TikTok's e-commerce recommendation system, HELIX consistently improves offline CTR AUC, CVR AUC, and other ranking metrics. In online A/B tests, it achieves an approximately 6% increase in e-commerce video GMV per user.

cs.IR↗
arXiv2026

Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents

LLM agents often admit multiple high-quality solutions to the same task, differing in reasoning structure, tool-use pattern, or interaction trajectory. Yet existing notions of diversity in LLM post-training are mostly implicit, arising from general stochasticity and regularization mechanisms rather than explicitly targeting task-relevant behavioral variation. While such implicit diversity can be useful, it does not directly specify which forms of behavioral variation should be encouraged for a given task. In this work, we study explicit trajectory diversity in RL-based post-training for LLMs. Our key idea is to define diversity through user-specified, task-specific trajectory descriptors, which map each sampled trajectory to an interpretable behavioral representation, and then measure diversity as a set-level functional over the resulting descriptor matrix. Building on this formulation, we introduce Trajectory-guided Joint Policy Optimization(TJPO), a single-policy framework that optimizes explicit diversity over sampled trajectory groups, avoiding the need for population-based policy training, and instantiate it within group-based policy optimization through trajectory-level learning signals. This design makes the diversity objective both interpretable and controllable. Experiments on Sokoban and ALFWorld show that TJPO improves task-specific trajectory diversity while maintaining competitive task performance. Descriptor and trajectory analyses show that the learned variation follows the specified behavioral dimensions and includes distinct successful strategies. Extra experiment results suggest that explicitly shaping trajectory diversity can help LLM agents satisfy user requirements and remain effective when task conditions change.

cs.LG↗
arXiv2026

D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders

Sparse autoencoders (SAEs) reveal visual structure in diffusion transformers (DiTs), but interpreting a feature does not establish whether it can be used to control generation. We introduce D-Scope (Diffusion Scope), a framework that connects feature interpretation to generation control through shared visual evidence. D-Scope aggregates SigLIP~2 embeddings of highly activating image patches into visual centroids. Matching target text descriptions against these visual centroids in the shared image-text embedding space then enables retrieval of individual features without per-feature text annotations. The underlying patches provide evidence for inspecting each selection, while spatially masked interventions test the corresponding decoder direction at varying strengths under fixed generation conditions. We characterize 150 SAEs across two model families and five layers, and introduce a benchmark of 100 target concepts with ten contexts each spanning under-specified and explicit-conflict conditions. Our empirical results show that high reconstruction fidelity can coexist with low dictionary utilization and limited visual-evidence coverage. Under per-case best-of-sweep strength selection, contrastive retrieval yields larger mean regional SigLIP~2 gains than direct retrieval across the tested steering configurations, without consistently improving outside-region preservation. D-Scope provides an inspectable framework for evaluating sparse DiT features through their visual evidence and the effects of their decoder directions on generation. The demo is available at https://jiahaozhang-public.github.io/d-scope/.

cs.CV↗
arXiv2026

EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Action

Vision-language-action (VLA) policies emphasize semantic understanding, whereas world-action models (WAMs) learn predictive representations of environment dynamics. Systems that expose a policy to both sources often still concentrate action computation on a single expert. We present EWAM, an action-centric unified embodied model whose asymmetric joint attention lets action tokens read semantic, current-visual, predicted-future, and action information at every layer while the perceptual experts retain their distinct roles. Without layer-wise supervision, EWAM develops an emergent depth-wise specialization: action queries attend mainly to vision-language features in shallow layers, to predicted future frames in intermediate layers, and to action tokens themselves in deep layers. This handoff replicates across tasks and is stable across denoising steps. Checkpoint tracking and causal interventions show that it is learned and that action generation depends on it. EWAM is pretrained in two separate regimes, one on cross-embodiment robot trajectories and one on human egocentric video. In simulation and real-robot experiments, it surpasses existing VLA, WAM, and hybrid baselines. Human egocentric data improve both cross-embodiment transfer and real-robot robustness, and subtask-phase supervision improves long-horizon completion. Together, these results suggest that unified embodied learning can induce an ordered internal progression from semantic understanding, through visual foresight, to action formation.

cs.RO↗
arXiv2026

Turbo Harness: Instance-Adaptive Harness Optimization

Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations typically produce a single global harness that is applied uniformly across task instances. However, a harness that works well on average may not be optimal for every instance. We introduce Turbo Harness, a framework that can adapt a globally optimized harness to each instance by reusing information generated during the original optimization process. Specifically, Turbo Harness recycles artifacts produced during a completed global harness optimization run, and summarizes them into a structured playbook. We train a harness editor to leverage this prior optimization experience to generate instance-specific patches to the global harness. At inference time, the editor uses the instance and the playbook to construct a tailored harness in which the execution model operates. Through numerical experiments, we show that Turbo Harness consistently outperforms existing harness optimization baselines across seven benchmarks spanning interactive agent tasks, software engineering, and long-horizon terminal tasks.

cs.AI↗