Searcharxiv⌕ Search

arXiv subjects

Han Wang

Publications and source records attributed to Han Wang.

At least 55 records · Page 3Linked to original sources
arXiv2026

Dynamics Models for Offline Hyperparameter Selection in Real-World RL

A key obstacle to deploying reinforcement learning in real-world systems is hyperparameter selection, particularly when simulators are unavailable and online experimentation is costly. Prior work has proposed calibration models trained on offline data to approximate environment dynamics and enable offline hyperparameter selection, but these methods have so far been evaluated only in simple simulated settings. In this paper, we present the first application of calibration models in a real-world industrial setting: a municipal water treatment plant. We evaluate several calibration model approaches, including a k-nearest neighbors model with a Laplacian distance metric, on high-dimensional, non-stationary sensor data for nexting prediction tasks. Our results show that these models can generate realistic long-horizon rollouts and recover meaningful hyperparameter sensitivity trends. We further examine how calibration models scale to year-long datasets, how they support the selection of fine-tuning learning rates for pre-trained agents, and how robust they are under distribution shift. Overall, our findings provide a proof of concept for using offline dynamics models to support RL deployment in real-world environments, while highlighting important practical challenges for future work.

cs.LG↗
arXiv2026

Beyond Imitation: Auditing the Recoverability of Reasoning in Distilled Models

A correct teacher solution becomes useful supervision when the receiving student can continue its reasoning. We measure this compatibility with prefix recovery: after revealing 25%, 50%, or 75% of a verified solution, we test whether the student completes it correctly. We connect recovery to the cosine conflict between cross-entropy and reverse-KL gradients over the full vocabulary. Across adjacent Qwen3 teacher-student pairs from 0.6B to 8B parameters, reverse-KL distillation delivers its most consistent mathematical and code improvements for the two students below 2B parameters. On a fixed cohort of 1,000 trajectories, average prefix recovery rises from 71.0% to 91.9% as student size increases from 0.6B to 4B, and the robust-fragile recovery gap contracts from 46.0 to 14.4 percentage points. With the teacher fixed at 8B, conflict separation falls from 0.993 to 0.233. An independent objective intervention finds the largest reverse-KL rescue on fragile trajectories. The three measurements locate the same capacity-dependent transfer regime: distribution matching has the greatest headroom when correct traces remain unevenly recoverable. Prefix recovery provides a practical diagnostic for selecting costly distribution-level distillation.

cs.LG↗
arXiv2026

Solver-Guided Reasoning for Mixed-Equilibrium Strategies

Reasoning in large language models (LLMs) is often grounded in human text, human demonstrations, and human-generated rationales. For equilibrium reasoning in complex games, however, relying on human data can be suboptimal. In fact, human play is often guided by intuition and heuristics and can deviate substantially from game equilibrium. This discrepancy is amplified in games with mixed-strategy equilibria, where human data is heavily biased toward pure strategies. Consequently, conditioning LLMs on this data yields weak game strategies. To grant LLMs the reasoning capacity in games, in this work, we study how to elicit equilibrium play using solver output. We propose Mixed-Strategy Decision Tree (MDT), which articulates the silent optimality of the equilibrium into sparse strategic rules that both humans and LLMs could understand. Using solver output rather than human annotation allows us to extend the input to arbitrarily new states and continuations. We instantiate this study on No-Limit Texas Hold'em by querying a solver oracle for over \textbf{250 million mixed-strategy decisions}; MDT together with other techniques \textbf{reduces the $\ell_1$ distance to the equilibrium by $52.6\%$} across $8$ different LLM configurations. A Route-only ablation tests the incremental contribution of the shadow-based contrast, while complete River-endgame and Liar's Dice experiments evaluate strategic fidelity and portability beyond the original NLH communication setting.

cs.LG↗
arXiv2026

RegionDet: A Benchmark for Region Detection Beyond Object Instances

Object detection is a fundamental task in computer vision and has achieved remarkable progress on standard benchmarks by localizing discrete and well-bounded object instances. However, many visual targets in real-world scenarios are not individual objects, but regions defined by visual states, scene context, object relations, and human activities, such as construction areas, damaged road regions, queues, group conversations, and vendor regions. Existing detection benchmarks are mainly built around object instances, providing limited support for systematically evaluating such region targets. To address this gap, we introduce Region Detection, a task that extends conventional object detection beyond object instances, and construct RegionDet, a benchmark for region target localization. RegionDet contains eight region categories, including Construction, Crossing, Damage, Queuing, Talking, Vendor, Waiting, and Walking, with COCO-style bounding-box annotations and evaluation protocols. We systematically evaluate representative closed-set and zero-shot/open-vocabulary detectors on RegionDet. Results show that closed-set detectors can partially learn region-level patterns under supervision, while zero-shot/open-vocabulary detectors struggle severely, revealing the strong object-centric bias of current vision-language detectors. Further analyses highlight key challenges in Region Detection, including weak boundary cues, strong context dependency, and insufficient relation-level region understanding. The RegionDet will be released.

cs.CV↗
arXiv2026

Beyond Motion Cues and Structural Sparsity: Revisiting Small Moving Target Detection

Small moving target detection is crucial for many defense applications but remains highly challenging due to low signal-to-noise ratios, ambiguous visual cues, and cluttered backgrounds. In this work, we propose a novel deep learning framework that differs fundamentally from existing approaches, which often rely on target-specific features or motion cues and tend to lack robustness in complex environments. Our key insight is that small target detection and background discrimination are inherently coupled, even cluttered video backgrounds often exhibit strong low-rank structures that can serve as stable priors for detection. We reformulate the task as a tensor-based low-rank and sparse decomposition problem and conduct a theoretical analysis of the background, target, and noise components to guide model design. Building on these insights, we introduce TenRPCANet, a deep neural network that requires minimal assumptions about target characteristics. Specifically, we propose a tokenization strategy that implicitly enforces multi-order tensor low-rank priors through a self-attention mechanism. This mechanism captures both local and non-local self-similarity to model the low-rank background without relying on explicit iterative optimization. In addition, inspired by the sparse component update in tensor RPCA, we design a feature refinement module to enhance target saliency. The proposed method achieves state-of-the-art performance on two highly distinct and challenging tasks: multi-frame infrared small target detection and space object detection. These results demonstrate both the effectiveness and the generalizability of our approach.

cs.CV↗
arXiv2026

The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Proposals

Frontier coding models now match or exceed strong human reference points on programming benchmarks, yet benchmark success does not imply maintainable software. Prompt-driven "vibe coding" is additive: new branches, guards, and fallbacks accumulate faster than obsolete logic is removed. We study the inverse problem-how an Al system should remove code when execution-verification capacity is finite. We formulate redundant-code reduction as proposal scheduling: a ranker orders single-statement deletion candidates, an execution suite accepts the first candidate that passes, and a budget bounds how many candidates may be tested. Our central observation is that candidate order, not model confidence, is the control surface a deployment can reason about. DELSCOUT instantiates two schedules. Given representative target-domain validation, a five-slot budget spends three slots on deterministic shortest-first candidates and two on complementary learned candidates; across nine MBPP replications with 0.5B, 0.6B, and 8B rankers this raises verified-deletion coverage by 9.5% relative (+6.7 accepted tasks) while consuming slightly fewer verifier calls than the matched static baseline. Without such validation the same rankers can lose coverage under shift, so we instead evaluate the complete static prefix first and append learned candidates only afterwards; for a deterministic verifier this makes coverage and character reduction non-decreasing by construction, at a measured 4.8-62.5% increase in verifier calls. MBPP+ then erases the in-domain advantage, showing that scheduling governs search while the test suite alone governs what "preserving behavior" means. The result is an auditable division of labor: models widen the search for removable code, order bounds the damage a mis-ranked proposal can do, and execution retains authority over every committed deletion.

cs.SE↗
arXiv2026

When Search Teaches Style: Causal Internalization of Tactical Priors in AlphaZero

AlphaZero is normally evaluated as one agent: a policy-value network fused with Monte Carlo tree search. That fusion hides a causal question. When self-play search is given a useful prior, does the network absorb the induced behavior, or does the behavior stay rented from search at test time? We answer with Cross-Phase Prior Intervention (CPI), which switches a root-level tactical prior on and off independently during training and during evaluation, separating the prior's online effect from the learned residual it leaves in the weights. The endpoint is deliberately narrow: how often a network discharges a forced defensive obligation when no search-time guidance is available. On a sealed one-shot final test in 9x9 Gomoku and 19x19 Go, deleting the prior still leaves a large residual response rises from 13.8% to 26.3% in Gomoku and from 0.6% to 33.8% in Go-and soft reweighting teaches as well as hard action restriction, so pruning legal actions is not the mechanism. The same cross bounds the claim: re-enabling the prior restores nearly 100% response, leaving dependence gaps of 73.7 and 65.8 points. A latched-position evaluation localizes the residual to trained geometry-absent at the shared initialization, emerging over training, worth +17.3 points on in-distribution defenses but only +1.3 on structurally novel ones. Search is therefore best read as a training-time behavioral curriculum whose lessons are real, partial, and geometry-bound, and online competence and internalized competence are different estimands that a diagonal ablation cannot tell apart.

cs.LG↗
arXiv2026

MoWorld: A Flash World Model

The future of World Models depends not only on scaling model capability, but also on scaling practicality and inference efficiency. High-frame-rate inference enables responsive perception, planning, and control in real-world autonomous systems. To this end, we present MoWorld, a cost-effective yet high-performance Flash World Model with an end-to-end framework spanning data generation, pre-training, distillation, and efficient inference, enabling up to 50 FPS real-time interaction with cinematic visual quality without the need of high-end GPUs. To enable large-scale real-world deployment, MoWorld jointly optimizes model capability and cost throughout the entire development pipeline. Specifically, unlike existing approaches that primarily rely on large-scale video corpora, MoWorld is built upon a scalable 3D-native data engine accumulated from our large-scale 3D vision and generative modeling pipeline, enabling the efficient construction of geometrically consistent training data across diverse real-world and synthetic environments. Based on this foundation, a curriculum cross-frame pre-training strategy for stable and scalable World Model learning, an efficient denoising-step distillation algorithm to reduce diffusion training cost, and a mixed-precision parallel inference framework for low-cost real-time deployment. MoWorld is the first real-time interactive World Model built on the Neural Processing Unit (NPU) and can achieves up to 50 FPS in such the devices, enabling practical and efficient deployment at scale. Comprehensive evaluations demonstrate that MoWorld achieves leading performance; notably, its average inference cost is only 30\%-50\% of that of existing World Models, providing a practical foundation for large-scale real-world applications of World Models. We also demonstrate diverse applications of MoWorld.

cs.CV↗
arXiv2026

Advancing Relevance Measurement with Vision-Language Models for Web-Scale Search

Relevance evaluation plays a crucial role in personalized search systems, serving as a guardrail alongside user engagement metrics to ensure that search results align with user queries and intent. While human annotation is the traditional method for relevance evaluation, its high cost and long turnaround time limit its scalability. In this work, we present a VLM-based automated relevance evaluation pipeline deployed within Pinterest Search for online A/B experiments. We rigorously validate the alignment between VLM-generated judgments and human annotations, demonstrating that VLMs can provide reliable relevance measurement for experiments while greatly improving the evaluation efficiency. Leveraging VLM-based labeling further unlocks opportunities to expand the query set, optimize sampling design, and efficiently assess a wider range of search experiences at scale. This approach leads to higher-quality relevance metrics and significantly reduces the Minimum Detectable Effects (MDEs) in online experiment measurements.

cs.IR↗
arXiv2026

Cognitive World Model for Progressive BDI/E Trajectory Evaluation of Conversational Agents

As LLM-based conversational agents advance toward increasingly open-ended and interaction-intensive scenarios, task completion alone provides an incomplete assessment of their effectiveness. The evolution of users' internal states, including beliefs, desires, intentions, and emotions (BDI/E), serves as an intermediate signal connecting agent behaviors with interaction outcomes and reflects how conversational strategies shape users during multi-turn interactions. However, existing evaluation paradigms primarily focus on surface-level responses or final outcomes, providing limited insight into the underlying cognitive processes. This limitation makes it difficult to diagnose why agents succeed or fail and to optimize their interaction strategies. To address this challenge, we propose Cognitive World Model (CogWM), an LLM-based cognitive user model that jointly models users' BDI/E states and corresponding responses, enabling explicit cognitive trajectory tracking. Trained on 150K user-turn samples with Qwen3-14B, CogWM achieves superior performance over existing user simulation baselines in both response fidelity and cognitive state understanding. Interactions with six state-of-the-art LLMs demonstrate that CogWM enables progressive comparison of agents through cognitive trajectories, revealing distinct agent patterns and complementary relationships between cognitive evolution and behavioral outcomes.

cs.AI↗
arXiv2026

RRAM-DP: Device-Calibrated Differential Privacy for In-Memory Edge Learning

Edge Artificial Intelligence of Things (AIoT) systems often collect sensitive data in situ, raising serious privacy concerns. Resistive-switching random-access memory (RRAM) is an attractive substrate for efficient AIoT thanks to its multi-bit storage and compute-in-memory (CiM) capabilities, while its inherently stochastic write behavior provides a natural source of randomness that can be leveraged for differential privacy (DP) protection. Yet how to transform this device-level randomness-typically viewed as detrimental to accuracy-into a principled randomized mechanism while preserving model utility remains underexplored. We propose RRAM-DP, a hardware-algorithm co-design that relaxes RRAM write-verify operations to inject calibrated noise for inherently (epsilon, delta)-DP with formal DP analysis; together with pretraining techniques, it renders a novel private, high-utility CiM training paradigm. On CIFAR-10/100, STS-B, and SST-2, RRAM-DP-SGD incurs at best only a 3.8% accuracy drop at (epsilon=2, delta=O(1/n))-DP relative to non-private SGD. At the same privacy level, RRAM-DP-SGD delivers up to 57x and 3.2x energy savings and 2.7x and 1.8x speedups over A100 and DiVa-GEMM, respectively. These results point toward efficient, privacy-preserving in-memory training on RRAM at the edge.

cs.CR↗
arXiv2026

You Only Look Omni Gradient Backpropagation for Moving Infrared Small Target Detection

Moving infrared small target detection is a key component of infrared search and tracking systems, yet it remains extremely challenging due to low signal-to-clutter ratios, severe target-background imbalance, and weak discriminative features. Existing deep learning methods primarily focus on spatio-temporal feature aggregation, but their gains are limited, revealing that the fundamental bottleneck lies in ambiguous per-frame feature representations rather than spatio-temporal modeling itself. Motivated by this insight, we propose BP-FPN, a backpropagation-driven feature pyramid architecture that fundamentally rethinks feature learning for small target. BP-FPN introduces Gradient-Isolated Low-Level Shortcut (GILS) to efficiently incorporate fine-grained target details without inducing shortcut learning, and Directional Gradient Regularization (DGR) to enforce hierarchical feature consistency during backpropagation. The design is theoretically grounded, introduces negligible computational overhead, and can be seamlessly integrated into existing frameworks. Extensive experiments on multiple public datasets show that BP-FPN consistently establishes new state-of-the-art performance. To the best of our knowledge, it is the first FPN designed for this task entirely from the backpropagation perspective.

cs.CV↗
arXiv2026

Effective Receptive Field Ordering Matters for Infrared Small Target Detection

In this work, we investigate a previously unexplored architectural dimension for infrared small target detection: the organization of effective receptive fields (ERFs) during feature refinement. Unlike existing approaches that primarily improve individual feature operators, we argue that ERF organization constitutes an architectural dimension independent of receptive field design itself, and formulate deep feature transformation as a progressive residual correction process, from which a theoretical framework for ERF scheduling is established. Specifically, we reveal that ERF refinement is governed by two fundamental properties: scale-frequency correspondence, which aligns different ERF scales with distinct residual frequency characteristics, and nonlinear non-commutativity, which makes different ERF orderings produce fundamentally different refinement trajectories. Together, these properties show that ERF organization, rather than ERF scale alone, governs refinement dynamics. Guided by these principles, we propose Receptive Field Ordering Network (RFONet), which realizes hierarchical ERF scheduling through a multigrid-inspired V-cycle strategy using only standard $3\times3$ convolutions. RFONet achieves state-of-the-art performance on multiple benchmarks with only 1.16M parameters and over 157 FPS inference speed. Beyond empirical performance, our theoretical analysis provides theoretical guarantees for stable residual refinement under perturbations, frequency shifts, and partial occlusions, which are consistently reflected in superior noise robustness and cross-dataset generalization. Finally, our framework reformulates ERF organization as a task-dependent optimization objective, providing a principled foundation for future adaptive receptive field scheduling.

cs.CV↗
arXiv2026

Constraining Dipole Radiation with Multiband Gravitational Waves from Eccentric Binary Black Holes

Dipole-radiation-like deviations from general relativity are most prominent during the early inspiral of compact binaries, making space-ground multiband observations a potential probe of such effects. In the same regime, orbital eccentricity can leave a significant imprint on the waveform and is therefore essential for robust dipole-radiation constraints. For the first time we present a multiband Bayesian inference pipeline for stellar-mass binary black holes that simultaneously incorporates eccentricity and a theory-agnostic dipole-radiation correction. We find strong degeneracies among the dipole parameter, chirp mass, and eccentricity, showing that eccentricity can broaden the inferred dipole posterior by opening an additional degeneracy direction. Even so, for a GW231123-like source, one year of TianQin or LISA observation with ground-informed priors from a next-generation detector network can still constrain the dipole parameter to $|b|\lesssim\mathcal{O}(10^{-7})$ under inference with noisy data. Our results show that multiband binary black hole observations provide a promising and distinct channel for testing theory-agnostic dipole radiation, while also highlighting the need for more complete waveform modeling in future precision tests of gravity.

gr-qc↗
arXiv2026

Gravitational Wave Astronomy With TianQin

The opening of the gravitational wave window has significantly enhanced our capacity to explore the universe's most extreme and dynamic sector. In the mHz frequency range, a diverse range of compact objects, from the most massive black holes at the farthest reaches of the Universe to the lightest white dwarfs in our cosmic backyard, generate a complex and dynamic symphony of gravitational wave signals. Once recorded by gravitational wave detectors, these unique fingerprints have the potential to decipher the birth and growth of cosmic structures over a wide range of scales, from stellar binaries and stellar clusters to galaxies and large-scale structures. The TianQin space-borne gravitational wave mission is scheduled for launch in the 2030s, with an operational lifespan of five years. It will facilitate pivotal insights into the history of our universe. This document presents a concise overview of the detectable sources of TianQin, outlining their characteristics, the challenges they present, and the expected impact of the TianQin observatory on our understanding of them.

astro-ph.GA↗
arXiv2026

Quantum many-body mixed phase space revealed by hybrid feedback control

Understanding how complex systems transition between order and chaos is a central challenge of nonequilibrium physics. While weak perturbations of classical integrable systems give rise to a mixed phase space of coexisting regular and chaotic trajectories, analogous behavior in interacting quantum many-body systems has remained elusive. Here we develop and experimentally implement a hybrid quantum-classical feedback protocol that autonomously discovers and stabilizes long-lived regular trajectories in a superconducting quantum processor. Each iteration combines short-time quantum evolution with classical optimization that projects the dynamics back onto a low-entanglement variational manifold, effectively distilling coherence from chaotic evolution. The stabilized trajectories reveal a quantum many-body mixed phase space emerging from nonlinear variational dynamics, without a direct analogue in classical or few-body quantum systems. Our results establish a versatile framework for algorithmic discovery and control of coherent dynamics previously inaccessible to experiment.

quant-ph↗
arXiv2026

Parameter Efficient Machine Unlearning on Hybrid Resistive Memory based Compute-in-Memory Accelerators

Resistive memory compute-in-memory accelerators provide energy efficient analogue matrix vector multiplication for neural network inference, but frequent reprogramming of analogue weights remains costly because of device variability and iterative write and verify operations. This limitation hinders their use in edge model adaptation, including approximate machine unlearning and continual learning, where model parameters may need to be updated repeatedly in response to data deletion requests or newly arriving tasks. Here we present a co-design approach across hardware and software that maps frozen pretrained weights to analogue resistive memory arrays while placing trainable low rank adaptation branches in SRAM connected digital compute. By using LoRA style parameter efficient updates, the proposed scheme confines adaptation to a small set of digital parameters and avoids repeated reprogramming of the analogue backbone. To our knowledge, this work provides the first experimental demonstration of approximate machine unlearning on a fabricated resistive memory CIM accelerator. We validate the framework on a 180 nm 128x128 1T1R resistive-memory macro for face recognition, and through circuit-accurate simulations for speaker authentication and stylized image generation tasks, owing to the substantial model sizes involved. Compared with a baseline that directly updates analog weights, our hybrid mapping reduces analog training/update cost by up to 148x, on-chip deployment overhead by up to 388x, and inference energy by up to 59x, while preserving competitive task performance. These results show that hybrid analogue-digital LoRA mapping can enable efficient post-deployment adaptation on RM-CIM hardware, although formal machine-unlearning guarantees and large-scale system integration remain open challenges.

cs.ET↗
arXiv2026

Sledgehammer or Scalpel? A Fine-grained Adaptive Framework for Implicit Hate Speech

Unlike explicit attacks with obvious profanity, implicit hate speech hides malice within seemingly compliant expressions through metaphors and contextual hints, making its detection in online content review challenging. While existing PLM- or LLM-based methods perform well, they typically apply a single reasoning process to all samples. This overlooks fine-grained linguistic nuances and causes unnecessary computation for simpler cases. We observe that online hate speech is not monolithic but manifests in varied forms. We therefore define three fine-grained categories: Shallow, Targeted, and Context-Dependent. Accordingly, we propose Fine-grained Adaptive Implicit Hate speech Detection (FAID), a novel framework that first performs fine-grained classification and then adapts to specific categories. Specifically, for Shallow samples with surface-identifiable intents, the framework adopts lightweight prompt-tuning for rapid classification; for Targeted comments that bind malicious intent to concealed targets, we design knowledge augmentation to iteratively refine the model and reveal hidden targets; for Context-Dependent comments lacking background information, we utilize an agentic framework that automatically generates prompts to evolve context, infer missing background information and identify ambiguous malicious intents. This adaptive architecture focuses computational resources on complex implicit samples while avoiding redundant reasoning for shallow samples. Experiments on four benchmark datasets demonstrate that FAID significantly outperforms SOTA baselines.

cs.CL↗