arXiv subjects

Hanlin Wu

Publications and source records attributed to Hanlin Wu.

At least 19 recordsLinked to original sources

arXiv2026

Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation

Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single generalist student via dense, token-level reward supervision. Despite its practical success, the optimization dynamics governing multi-teacher capability integration remain poorly understood, and open, rigorously reproducible recipes are conspicuously lacking. In this work, we establish a controlled M-OPD benchmark on SmolLM3-3B-Base with oracle routing, isolating capability integration from routing ambiguity. Our investigation reveals a pronounced capability integration gap: standard M-OPD captures only 35.6% of the available headroom relative to a domain-routed oracle ensemble, with concise tasks such as instruction following suffering severe degradation and premature stagnation. Crucially, we show that this failure stems not from gradient conflict, but from a severe misallocation of the token-level optimization budget. This pathology is driven by three orthogonal factors: structural sequence-length disparities across domains, dynamic convergence drift due to non-uniform learning rates, and multi-step reward staleness from asynchronous policy updates. To resolve these imbalances, we introduce Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh. Together, these mechanisms systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student. We fully open-source our end-to-end post-training recipe, training trajectories, and evaluation suites on an academically accessible hardware budget.

cs.LG↗

arXiv2026

Toward Blockage-Resilient 6G-V2X Connectivity: Semi-Distributed Bandit with Dynamic Arm Set for mmWave HetNets

The vision for 6G vehicle-to-everything (V2X) communications demands reliable, adaptive connectivity for fully autonomous driving across complex dynamic environments. Millimeter-wave (mmWave) user association (UA) in heterogeneous vehicular networks presents a particularly demanding instance of this problem, where dynamic blockages and rapid channel variations continuously undermine the stationary reward assumptions of traditional multi-armed bandit (MAB) frameworks. This paper proposes a fully distributed blockage-aware non-stationary dynamic bandit algorithm (BAND) and its semi-distributed extension S-BAND for cooperative learning across vehicles. Blockage prediction is incorporated into the change-detection (CD) mechanism to suppress false alarms, while a dynamic base station (BS) set management scheme balances exploration and exploitation across large-scale BS deployments without requiring centralized channel state information (CSI) acquisition or offline training. In S-BAND, vehicles accumulate BS reward estimates as local knowledge and periodically upload them to the macro base station (MBS), which aggregates them into cluster-based central knowledge. A trajectory-aligned knowledge (TAK) region is proposed to capture the spatial correlation of mmWave channel characteristics. A knowledge inheritance fidelity (KIF) metric is introduced to quantify knowledge transfer quality. Simulation results on a realistic urban topology show that BAND and S-BAND achieve 34.9% and 59.4% regret reduction relative to a centralized MAB baseline, with performance gains sustained across blockage rates ranging from 10% to 50%. The proposed TAK region consistently outperforms the traditional K-means clustering scheme under both fidelity criteria.

cs.ET↗

arXiv2026

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily heuristic and fail to identify the essential cause of PPO-Clip's failure. This work reveals the fundamental flaw of PPO-Clip: it implicitly measures policy discrepancy using Euclidean metric, which is theoretically inconsistent with the intrinsic geometry on the policy Riemannian manifold. This geometric mismatch results in overly conservative updates in low-probability regions while aggressive in high-probability regions, ultimately collapsing exploration. To correct this geometric flaw, we propose Riemannian Isometric Policy Optimization (RIPO), which guarantees isometric policy updates on the Riemannian manifold, effectively balancing exploration and exploitation. We further show that RIPO achieves a favorable bias-variance trade-off, which stabilizes optimization. Extensive experiments demonstrate that RIPO significantly surpasses existing LLM RL algorithms across seven competition-level benchmarks (up to 60% improvement over GRPO on AIME24).

cs.LG↗

arXiv2026

Weak-to-Strong Generalization via Direct On-Policy Distillation

Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because the target model must generate many rollouts during training. As models scale, post-training itself becomes a bottleneck. We study a weak-to-strong alternative: run RL on a smaller model where rollouts are cheaper, then reuse what that RL run learned to improve a stronger target model. Directly distilling the post-RL weak teacher is not enough, because the teacher's final policy mixes useful RL gains with the limitations of the smaller model. We propose Direct On-Policy Distillation (Direct-OPD), which transfers the teacher's RL-induced policy shift instead. Direct-OPD compares the post-RL teacher with its own pre-RL reference and treats their log-ratio as a dense implicit reward for the student. In plain terms, the checkpoint pair tells us which actions RL made the weak model more or less likely to take, and Direct-OPD applies that signal on the stronger student's own on-policy states. This directly reuses the weak model's RL supervision signal without running sparse-reward RL on the target model. Empirically, Direct-OPD consistently leverages weaker teachers to improve stronger target models; notably, it boosts Qwen3-1.7B from 48.3% to 58.3% on AIME 2024 in just 4 hours on 8 A100 GPUs. It outperforms step-matched direct RL and enables the sequential composition of multiple policy shifts. Our results show that RL outcomes can be reused across model scales as implicit reward signals, not merely as final models to imitate.

cs.LG↗

arXiv2026

Spectral Rewiring for Exploration, Purification, and Model Merging

Reinforcement learning has become a standard post-training recipe for large language models, but dense full-parameter updates create two deployment-relevant bottlenecks: suppressed reasoning performance, often reflected by premature saturation of test-time scaling, and interference when consolidating multiple capabilities through multi-domain training or model merging. We show that the reasoning-effective component of these updates is largely concentrated in the base model's spectral space, motivating Subspace-Aligned Rewiring (SAR), a post-hoc editing method that retains this spectral core while removing orthogonal components. SAR therefore preserves reasoning gains and filters residual update directions that suppress performance or amplify cross-domain interference. Across several model families and scales, SAR extracts compact reasoning cores using as little as approximately 0.58% of total parameters: it preserves over 99% of post-training performance and improves high-k exploration in mathematical reasoning, and generalizes to agentic coding by improving six of seven open benchmarks on an in-house model. SAR also purifies mixed-domain training updates by releasing suppressed coding capability while maintaining math reasoning and instruction following. It further enables model merging across experts, yielding cross-domain generalization that surpasses previous merging baselines and even the best single-domain experts. Overall, SAR shows that extracting reasoning-effective updates from parameter geometry can serve as a training-free mechanism to improve reasoning and multi-domain performance.

cs.LG↗

arXiv2026

Flow-based Gaussian Splatting for Continuous-Scale Remote Sensing Image Super-Resolution

High-resolution remote sensing images (RSIs) are crucial for Earth observation applications, yet acquiring them is often limited by sensor constraints and costs. In recent years, generative super-resolution (SR) methods, particularly diffusion models, have made significant progress. However, they typically require slow iterative inference with 40--1000 steps and exhibit limited flexibility in continuous-scale SR settings. To address these issues, we propose FlowGS, a generative reconstruction framework for arbitrary-scale SR of RSIs. FlowGS models the high-frequency detail representations between high- and low-resolution images and learns a continuous probability flow from noise to detail priors via flow matching (FM) constrained by shortcut consistency, thereby reducing generative complexity and improving inference efficiency. Additionally, we employ 2D Gaussian splatting to construct a continuous feature field, thereby enabling flexible reconstruction at arbitrary query locations. Experimental results show that FlowGS delivers competitive perceptual quality compared with existing methods in both continuous-scale and fixed-scale SR settings, with substantially improved inference efficiency.

cs.CV↗

arXiv2026

MapSR: Prompt-Driven Land Cover Map Super-Resolution via Vision Foundation Models

High-resolution (HR) land-cover mapping is often constrained by the high cost of dense HR annotations. We revisit this problem from the perspective of map super-resolution, which enhances coarse low-resolution (LR) land-cover products into HR maps at the resolution of the input imagery. Existing weakly supervised methods can leverage LR labels, but they typically use them to retrain dense predictors with substantial computational cost. We propose MapSR, a prompt-driven framework that decouples supervision from model training. MapSR uses LR labels once to extract class prompts from frozen vision foundation model features through a lightweight linear probe, after which HR mapping proceeds via training-free metric inference and graph-based prediction refinement. Specifically, class prompts are estimated by aggregating high-confidence HR features identified by the linear probe, and HR predictions are obtained by cosine-similarity matching followed by graph-based propagation for spatial refinement. Experiments on the Chesapeake Bay dataset show that MapSR achieves 59.64% mIoU without any HR labels, remaining competitive with the strongest weakly supervised baseline and surpassing a fully supervised baseline. Notably, MapSR reduces trainable parameters by four orders of magnitude and shortens training time from hours to minutes, enabling scalable HR mapping under limited annotation and compute budgets. The code is available at https://github.com/rikirikirikiriki/MapSR.

cs.CV↗

arXiv2026

Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration

Face restoration can be formulated as a continuous-time transformation between image distributions via Flow Matching (FM). However, standard FM typically employs independent coupling, ignoring the statistical correlation between low-quality (LQ) and high-quality (HQ) data. This leads to intersecting trajectories and high velocity-field curvature, requiring multi-step integration. We propose Shortcut-constrained Coupling Flow for Face Restoration (SCFlowFR) to address these challenges. By establishing a data-dependent coupling, we explicitly model the LQ-HQ dependency to minimize path crossovers and promote near-linear probability flow. Furthermore, we employ a conditional mean estimator to refine the source distribution's anchor, effectively tightening the transport cost and stabilizing the velocity field. To ensure stable one-step inference, a shortcut constraint is introduced to supervise average velocities over arbitrary intervals, mitigating discretization bias in large-step updates. SCFlowFR achieves state-of-the-art one-step restoration, providing a superior trade-off between perceptual fidelity and computational efficiency.

cs.CV↗

arXiv2026

CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation

GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general programming, large language models (LLMs) remain uncompetitive with compiler-based systems such as torch.compile for CUDA kernel generation. Existing CUDA code generation approaches either rely on training-free refinement or fine-tune models within fixed multi-turn execution-feedback loops, but both paradigms fail to fundamentally improve the model's intrinsic CUDA optimization ability, resulting in limited performance gains. We present CUDA Agent, a large-scale agentic reinforcement learning system that develops CUDA kernel expertise through three components: a scalable data synthesis pipeline, a skill-augmented CUDA development environment with automated verification and profiling to provide reliable reward signals, and reinforcement learning algorithmic techniques enabling stable training. CUDA Agent achieves state-of-the-art results on KernelBench, delivering 100\%, 100\%, and 92\% faster rate over torch.compile on KernelBench Level-1, Level-2, and Level-3 splits, outperforming the strongest proprietary models such as Claude Opus 4.5 and Gemini 3 Pro by about 40\% on the hardest Level-3 setting.

cs.LG↗

arXiv2026

SUG-Occ: Explicit Semantics and Uncertainty Guided Sparse Learning for Efficient 3D Occupancy Prediction

3D semantic occupancy prediction has emerged as a critical perception task for autonomous driving due to its ability to offer voxel-level semantic and geometric understanding of the environment. However, such a refined representation for large-scale scenes incurs prohibitive computation, posing a significant challenge to practical real-time deployment. To address this, we propose SUGOcc, an explicit semantics and uncertainty guided sparse learning framework for efficient occupancy prediction, which exploits the inherent sparsity of 3D scenes to reduce redundant computation while maintaining geometric and semantic integrity. Specifically, we first utilize semantic and uncertainty priors to suppress image projections from free space while employing explicit unsigned distance encoding to enhance geometric consistency, thereby producing a structurally sparse representation. Secondly, we introduce a cascade sparse completion module to enable efficient coarse-to-fine reasoning over the sparse representation via hyper cross sparse convolution, generative upsampling and adaptive pruning. Finally, we propose an object contextual representation (OCR) based mask decoder that refines the voxel-wise predictions through lightweight query-context interactions, thereby avoiding expensive attention operations over volumetric features. Extensive experiments on SemanticKITTI and Occ3D-Nuscenes benchmark demonstrate that the proposed approach outperforms the baselines, achieving notable improvements in both accuracy and efficiency across datasets.

cs.CV↗

arXiv2025

CaFTRA: Frequency-Domain Correlation-Aware Feedback-Free MIMO Transmission and Resource Allocation for 6G and Beyond

The fundamental designs of wireless systems toward AI-Native 6G and beyond are driven by the need for ever-increasing demand of mobile data traffic, extreme spectral efficiency, and adaptability across diverse service scenarios. To overcome the limitations posed by feedback-based multiple-input and multiple-output (MIMO) transmission, we propose a novel frequency-domain Correlation-aware Feedback-free MIMO Transmission and Resource Allocation (CaFTRA) framework tailored for fully-decoupled radio access networks (FD-RAN) to meet the emerging requirements of AI-Native 6G and beyond. By leveraging artificial intelligence (AI), CaFTRA effectively eliminates real-time uplink feedback by predicting channel state information (CSI) based solely on user geolocation. We introduce a Learnable Queries-driven Transformer Network for CSI mapping from user geolocation, which utilizes multi-head attention and learnable query embeddings to accurately capture frequency-domain correlations among resource blocks (RBs), thereby significantly improving the precision of CSI prediction. Once base stations (BSs) adopt feedback-free transmission, their downlink transmission coverage can be significantly expanded due to the elimination of frequent uplink feedback. To enable efficient resource scheduling under such extensive-coverage scenarios, we apply a low-complexity many-to-one matching theory-based algorithm for efficient multi-BS association and multi-RB resource allocation, which is proven to converge to a stable matching within limited iterations. Simulation results demonstrate that CaFTRA achieves stable matching convergence and significant gains in spectral efficiency and user fairness compared to 5G, underscoring its potential value for 6G standardization efforts.

eess.SY↗

arXiv2025

Neural Dynamics of AI-attributed Irony Reveal a Partial Intentional Stance

As Large Language Models (LLMs) are increasingly deployed as social agents and trained to produce humor and irony, a question emerges: when encountering witty AI remarks, do people interpret them as deliberate communicative acts? This study investigated whether people adopt an intentional stance, ascribing mental states to explain behavior, when comprehending AI-attributed irony. Irony provides a testbed because understanding it requires distinguishing intentional contradictions from unintended errors through pragmatic reanalysis. Using electroencephalography (EEG) to measure event-related potentials (ERPs), we compared behavioral and neural responses to identical ironic utterances attributed to either an AI companion or a human. We found that people do not fully adopt an intentional stance towards AI communication. Participants interpreted contextually incongruent utterances as irony significantly less often when attributed to an AI than when attributed to a human. Correspondingly, we observed attenuated neural responses to AI-attributed irony compared to human-attributed irony during both initial semantic processing (P200) and pragmatic reanalysis (P600). In addition, these neural responses were modulated by individual perceptions of AI sincerity and trustworthiness, with positive perceptions facilitating pragmatic comprehension by reducing cognitive effort. This suggests that adopting an intentional stance toward AI is a flexible and adaptive process, dynamically shaped by people's mental models of artificial agents. These findings reveal that despite advances in communicative competence, AI systems face a barrier to social agency: humans process input from artificial interlocutors with reduced ascription of intentionality. This has important implications for understanding human social cognition and for designing AI systems intended for social interaction.

cs.CL↗

arXiv2025

Structure leads and dominates comprehension in naturalistic reading

The hierarchical account and statistical or sequential account have long been framed as rival theories in explaining online comprehension. A lot of evidence has shown that both hierarchical and non-hierarchical factors can shape comprehension and the open question is no longer whether hierarchy contributes, but when and how strongly it does. We addressed the question with co-registered EEG and eye-tracking, treating syntactic depth as the variable for operationalizing hierarchical structure. On timing, hierarchical structure influenced reading before the eyes fixated a word: its neural effect emerged as early as 108 ms before fixation onset, over right-central regions, and the scanpath showed an anticipatory bias toward structurally central words. Both the transitional-probability analysis and the regression on fixation-related potentials supported this pre-fixational timing. In the transitional-probability analysis, readers preferentially moved between syntactically central words rather than following serial word order, showing that scanpaths are organized by syntactic depth rather than by linear adjacency. On strength, Bayesian network modeling showed that syntactic depth was the strongest predictor of departures from linear, word-by-word reading, outweighing lexical familiarity and surprisal. Taken together, the results indicate that hierarchical structure anticipatorily guides online comprehension at both the behavioral and neural levels, and dominates the reading path relative to statistical features.

cs.CL↗

arXiv2025

A funny companion: Distinct neural responses to AI- versus human-attributed humor

As artificial intelligence (AI) companions become capable of human-like communication, including telling jokes, understanding how people cognitively and affectively respond to AI-attributed humor becomes increasingly important. This study used EEG to compare how people process puns versus controls attributed to either an AI agent or a human. In an interaction task, participants guessed punchlines based on joke setups before they were disclosed by the interlocutor. Behavioral analysis revealed that participants rated AI- and human-attributed humor as comparably funny. However, neurophysiological data showed that AI-attributed humor elicited a reduced and sustained N400 effect compared to human-attributed humor, suggesting reduced cognitive effort in semantic conflict detection and resolution, or attenuated feedback-related processing. This was also accompanied by a larger late positive potential (LPP), reflecting intensified late-stage affective and evaluative processing. This likely reflects a process where the brain reconciles AI's delivery of culturally embedded puns with prior low expectations, leading to intensified affective engagement and interlocutor model updating. Individual differences in social perceptions further influenced neural responses. Higher perceived AI sincerity and trustworthiness were associated with a globally reduced N400, facilitating semantic integration for both humorous and non-humorous AI language. Additionally, increased AI trustworthiness predicted an enhanced LPP, indicating a more intensified updating of the interlocutor model during humor comprehension. These findings indicate that the brain's neural sensitivity to AI-attributed humor bypasses biases like algorithm aversion. This highlights the brain's adaptation to humor from a novel source and underscores humor's potential for fostering genuine engagement in human-AI social interaction.

cs.CL↗

arXiv2025

DeltaVLM: Interactive Remote Sensing Image Change Analysis via Instruction-guided Difference Perception

Accurate interpretation of land-cover changes in multi-temporal satellite imagery is critical for real-world scenarios. However, existing methods typically provide only one-shot change masks or static captions, limiting their ability to support interactive, query-driven analysis. In this work, we introduce remote sensing image change analysis (RSICA) as a new paradigm that combines the strengths of change detection and visual question answering to enable multi-turn, instruction-guided exploration of changes in bi-temporal remote sensing images. To support this task, we construct ChangeChat-105k, a large-scale instruction-following dataset, generated through a hybrid rule-based and GPT-assisted process, covering six interaction types: change captioning, classification, quantification, localization, open-ended question answering, and multi-turn dialogues. Building on this dataset, we propose DeltaVLM, an end-to-end architecture tailored for interactive RSICA. DeltaVLM features three innovations: (1) a fine-tuned bi-temporal vision encoder to capture temporal differences; (2) a visual difference perception module with a cross-semantic relation measuring (CSRM) mechanism to interpret changes; and (3) an instruction-guided Q-former to effectively extract query-relevant difference information from visual changes, aligning them with textual instructions. We train DeltaVLM on ChangeChat-105k using a frozen large language model, adapting only the vision and alignment modules to optimize efficiency. Extensive experiments and ablation studies demonstrate that DeltaVLM achieves state-of-the-art performance on both single-turn captioning and multi-turn interactive change analysis, outperforming existing multimodal large language models and remote sensing vision-language models. Code, dataset and pre-trained weights are available at https://github.com/hanlinwu/DeltaVLM.

cs.CV↗

arXiv2025

A Synthetic Benchmark for Collaborative 3D Semantic Occupancy Prediction in V2X-Enabled Autonomous Driving

3D semantic occupancy prediction is an emerging perception paradigm in autonomous driving, providing a voxel-level representation of both geometric details and semantic categories. However, its effectiveness is inherently constrained in single-vehicle setups by occlusions, restricted sensor range, and narrow viewpoints. To address these limitations, collaborative perception enables the exchange of complementary information, thereby enhancing the completeness and accuracy of predictions. Despite its potential, research on collaborative 3D semantic occupancy prediction is hindered by the lack of dedicated datasets. To bridge this gap, we design a high-resolution semantic voxel sensor in CARLA to produce dense and comprehensive annotations. We further develop a baseline model that performs inter-agent feature fusion via spatial alignment and attention aggregation. In addition, we establish benchmarks with varying prediction ranges designed to systematically assess the impact of spatial extent on collaborative prediction. Experimental results demonstrate the superior performance of our baseline, with increasing gains observed as range expands. Our code is available at https://github.com/tlab-wide/Co3SOP}{https://github.com/tlab-wide/Co3SOP.

cs.CV↗

arXiv2025

Single-Step Latent Consistency Model for Remote Sensing Image Super-Resolution

Recent advancements in diffusion models (DMs) have greatly advanced remote sensing image super-resolution (RSISR). However, their iterative sampling processes often result in slow inference speeds, limiting their application in real-time tasks. To address this challenge, we propose the latent consistency model for super-resolution (LCMSR), a novel single-step diffusion approach designed to enhance both efficiency and visual quality in RSISR tasks. Our proposal is structured into two distinct stages. In the first stage, we pretrain a residual autoencoder to encode the differential information between high-resolution (HR) and low-resolution (LR) images, transitioning the diffusion process into a latent space to reduce computational costs. The second stage focuses on consistency diffusion learning, which aims to learn the distribution of residual encodings in the latent space, conditioned on LR images. The consistency constraint enforces that predictions at any two timesteps along the reverse diffusion trajectory remain consistent, enabling direct mapping from noise to data. As a result, the proposed LCMSR reduces the iterative steps of traditional diffusion models from 50-1000 or more to just a single step, significantly improving efficiency. Experimental results demonstrate that LCMSR effectively balances efficiency and performance, achieving inference times comparable to non-diffusion models while maintaining high-quality output.

eess.IV↗

arXiv2025

Distinct social-linguistic processing between humans and large audio-language models: Evidence from model-brain alignment

Voice-based AI development faces unique challenges in processing both linguistic and paralinguistic information. This study compares how large audio-language models (LALMs) and humans integrate speaker characteristics during speech comprehension, asking whether LALMs process speaker-contextualized language in ways that parallel human cognitive mechanisms. We compared two LALMs' (Qwen2-Audio and Ultravox 0.5) processing patterns with human EEG responses. Using surprisal and entropy metrics from the models, we analyzed their sensitivity to speaker-content incongruency across social stereotype violations (e.g., a man claiming to regularly get manicures) and biological knowledge violations (e.g., a man claiming to be pregnant). Results revealed that Qwen2-Audio exhibited increased surprisal for speaker-incongruent content and its surprisal values significantly predicted human N400 responses, while Ultravox 0.5 showed limited sensitivity to speaker characteristics. Importantly, neither model replicated the human-like processing distinction between social violations (eliciting N400 effects) and biological violations (eliciting P600 effects). These findings reveal both the potential and limitations of current LALMs in processing speaker-contextualized language, and suggest differences in social-linguistic processing mechanisms between humans and LALMs.

cs.CL↗