arXiv subjects

Yongkang Zhang

Publications and source records attributed to Yongkang Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Stealthy in Semantics, Antagonistic in Space: Attacking Visible-Infrared Object Detectors via Object-Level Misalignment

Visible-infrared object detectors are used for robust perception under challenging illumination and weather conditions. Current physical attacks apply conspicuous patches to spatially aligned target regions, which are noticeable to human observers. Meanwhile, most of these methods only perturb the appearance within the aligned region, without explicitly targeting the correspondence between modalities or the fusion process. In this paper, we propose CamoShift, an adversarial framework for visible-infrared object detection. By combining visual camouflage with object-level infrared shifting, CamoShift breaks cross-modal spatial alignment and disrupts fusion. Specifically, the Semantic Camouflage Module (SCM) generates a stealthy camouflaged patch that can be attached to the host object and maintains its effectiveness in the infrared branch through an RGB-IR adapter. The Object-level Spatial Decoupling Module (OSDM) shifts the infrared target evidence in a scale-aware manner, so as to break object-level correspondence and disrupt cross-modal fusion. Then, the Harmonic Adversarial loss (HarAdv loss) further balances attack strength and visual stealth during optimization. To the best of our knowledge, we are the first to target both visual stealthiness and attack success in visible-infrared object detection. Extensive experimental results show that CamoShift achieves a superior balance between attack effectiveness and visual stealth. Code and models will be available on GitHub.

cs.CV↗

arXiv2026

On the Impossibility of Unbiased and Length-Invariant Policy Optimization with Outcome Rewards

Group Relative Policy Optimization (GRPO) is the dominant reinforcement learning algorithm for training reasoning capabilities in large language models, notably adopted by DeepSeek-R1. The recent improvement Dr. GRPO (COLM 2025) identifies the response-level length bias caused by per-trajectory length normalization in GRPO and proposes removing this normalization, claiming the resulting optimizer is "unbiased." We show that this claim is incomplete. Specifically, we establish an impossibility theorem: under the standard outcome reward + GRPO setting, no length-based weighting scheme can simultaneously achieve the following two properties. (P1) Gradient unbiasedness: the gradient estimator is an unbiased estimate of the true policy gradient. (P2) Length invariance: each trajectory's effective contribution to the gradient is independent of its token length. GRPO approximately satisfies P2 but violates P1; Dr. GRPO satisfies P1 but violates P2. We characterize the complete tradeoff spectrum via the parametric family f_alpha(L) = L^{alpha - 1}, where alpha = 0 recovers GRPO, alpha = 1 recovers Dr. GRPO, and provide quantitative analysis showing that Dr. GRPO's length bias can cause longer trajectories to dominate gradient updates by a factor proportional to the length ratio. Our results reveal that neither algorithm is universally "done right"; they occupy opposite ends of a fundamental and unavoidable tradeoff.

cs.LG↗

arXiv2026

Technical Report on the CVPR 2026@AdvML Workshop Challenge

Vision-language agents (VLAs) are increasingly used to interpret complex driving scenes and support safety-critical reasoning. This report presents the CVPR 2026@AdvML Workshop Challenge on adversarial multimodal attacks against autonomous-driving VLAs. Built on DriveLM-style multi-view visual question answering, the challenge represents each scene with six synchronized camera images and a structured collection of driving-related question-answer pairs. Participants generate adversarial images and suffix-only textual perturbations that induce model responses to deviate from reference answers while preserving image fidelity and limiting textual cost. The competition comprises two phases, with Phase II adding a hidden black-box model to assess transferability. We describe the task design, submission rules, evaluation protocol, and leaderboard results, and then examine five leading submissions for which technical reports were available. Across these reports, several recurring patterns emerge: image-side attacks are favored by the suffix penalty; scene-level, multi-view optimization is more effective than treating views in isolation; QA types and graph structure provide useful priors for allocating attack budget; feature-space objectives can improve black-box transfer; and typographic content embedded in camera images exposes a persistent vulnerability in driving VLAs. These findings provide a practical reference for future robustness evaluation and defense design in multimodal autonomous-driving systems.

cs.CV↗

arXiv2026

ThinkReset: Learnable Intermediate Interface Construction for Bounded-Context Long-Horizon Reasoning

Long chain-of-thought reasoning improves performance on complex problems, but it also introduces redundancy accumulation, context overflow, and error anchoring. We argue that under bounded context windows, the core bottleneck is not trajectory compression or test-time control, but the absence of a reusable intermediate interface that can replace discarded history and support continued solving. We further identify a key failure mode of outcome-reward-driven long-chain reinforcement learning: when the model has not solved the task before the window is nearly exhausted, the final-answer reward encourages premature guessing rather than continued careful reasoning. We propose ThinkReset, a text-space instantiation of this view. ThinkReset explicitly constructs reusable intermediate interfaces through interface writeback and reset, and directly optimizes post-reset continuation success. Across multiple long-horizon reasoning benchmarks, this perspective consistently improves success rates under fixed context windows.

cs.AI↗

arXiv2026

Design Conditions for Intra-Group Learning of Sequence-Level Rewards: Token Gradient Cancellation

Reinforcement learning for multi-step reasoning with large language models (LLMs) typically relies on sparse terminal rewards, which creates a poorly conditioned credit-assignment problem: the final feedback is propagated uniformly across all intermediate decisions. This leads to high gradient variance, unstable training, and many ineffective updates, ultimately limiting sustained model improvement. We propose a counterfactual-comparison framework for credit assignment. For each input, the framework samples multiple reasoning trajectories and treats their differences as implicit approximations to alternative decisions. This yields an implicit process-level advantage estimator that converts sparse terminal rewards into step-sensitive learning signals. Building on this framework, we introduce Implicit Behavior Policy Optimization (IBPO), which substantially improves training stability and the performance ceiling on mathematical and code-reasoning benchmarks. Our results point to a promising direction for unlocking the reasoning potential of LLMs.

cs.LG↗

arXiv2026

Rethinking the Comparison Unit in Sequence-Level Reinforcement Learning: An Equal-Length Paired Training Framework from Loss Correction to Sample Construction

This paper investigates the length problem in sequence-level relative reinforcement learning. We observe that, although existing methods partially alleviate length-related phenomena, a more fundamental issue remains insufficiently characterized: the comparison units used during training lack inherent comparability. Building on this observation, we propose a new perspective: the length problem should not be viewed merely as a loss-scaling or normalization bias, but rather as a \emph{comparison unit construction} problem. We further establish a sample-construction-based training framework that, instead of applying post-hoc corrections to unequal-length responses, proactively constructs equal-length, alignable, and comparable training segments during generation. Within this framework, we propose EqLen, a concrete method applicable to group-relative comparison algorithms such as GRPO, GSPO, and RLOO. Through dual-track synchronous generation, prefix inheritance, and segment masking, EqLen efficiently collects effective equal-length training segments and enables stable

cs.LG↗

arXiv2026

Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning

The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamentally in how to transform feedback provided only at the end of a sequence into fine-grained learning signals that can guide intermediate reasoning steps. Existing approaches either rely on outcome-level rewards for sequence-level optimization, which makes precise credit assignment difficult, or depend on externally constructed process supervision, which is costly and difficult to scale sustainably. To address this, we propose a new perspective: reinforcement learning for reasoning can be understood as the problem of internalizing outcome supervision into process supervision. From this perspective, we introduce a supervision-internalization method for reinforcement learning for reasoning, enabling the model to automatically extract process-level learning signals through identifying, correcting, and reusing failed reasoning trajectories, thereby achieving finer-grained policy optimization under outcome-only supervision. We further abstract this idea into a new training paradigm, in which the model continually generates and refines its own internal process supervision during reinforcement learning, opening a new path for fine-grained credit assignment in reinforcement learning for reasoning that differs from externally provided process supervision.

cs.LG↗

arXiv2026

Reducing Credit Assignment Variance via Counterfactual Reasoning Paths

cs.LG↗

arXiv2026

State commitment learning: training language models to distinguish computation from memory

Reasoning language models do not distinguish tokens used for computation from tokens that constitute persistent state: once generated, all hidden thoughts remain in context and influence future predictions. As a result, downstream reasoning may depend on failed attempts, dead ends, and private scratch work that should not be safely relied on later. We recast this phenomenon as a new training objective, state commitment learning: training models to explicitly distinguish information that should be committed as persistent state from temporary computation that can be discarded. We define a counterfactual criterion, persistent-state sufficiency, which makes it trainable and measurable whether an answer remains usable after hidden thoughts are erased. We then propose Counterfactual Erasure RL (CERL), which evaluates, under the same prefix, both a path that keeps hidden thoughts and a path that erases them, and gives reward only when the erasure path remains correct. We also introduce the Erasure Dependence Protocol and show across mathematics, long-chain logic, scientific QA, and multi-turn tool-use evaluation that CERL substantially reduces answer dependence on hidden thoughts without sacrificing accuracy, consistently outperforming correctness-only RL and long-answer SFT baselines.

cs.LG↗

arXiv2026

Scaffold-Mediated Post-Training: Co-Evolving Model Parameters and Procedural Scaffold Graphs

Post-training of large language models optimizes only parameters, while inference-time procedural scaffolds are typically designed independently of parameter training. This disconnect makes it difficult to automatically acquire and internalize complex strategies. We propose scaffold-mediated post-training: procedural scaffolds are organized into an evolvable graph structure that co-evolves with model parameters through discovery, distillation, and dynamic recompilation. We instantiate this paradigm as Skill Training. On FeatureBench, automatically discovered skills improve the passed rate by 8.1pp, and after progressive distillation the model still achieves a 27.7% passed rate without any external scaffold (distillation retention rate 85.2%, defined as post-distillation / with-skill passed rate), significantly outperforming standard SFT on the same data.

cs.CL↗

arXiv2026

MVSS: A Unified Framework for Multi-View Structured Survey Generation

Scientific surveys require not only summarizing large bodies of literature, but also organizing them into clear and coherent conceptual structures. However, existing automatic survey generation methods typically focus on linear text generation and struggle to explicitly model hierarchical relations among research topics and structured methodological comparisons, resulting in substantial gaps in structural organization and evidence presentation compared to expert-written surveys. To address this limitation, we propose MVSS, a multi-view structured survey generation framework that jointly generates and aligns citation-grounded hierarchical trees, structured comparison tables, and survey text. MVSS follows a structure-first paradigm: it first constructs a tree that captures the conceptual organization of a research domain, then generates comparison tables constrained by the tree structure, and finally uses both the tree and tables as joint structural constraints to guide outline construction and survey text generation. This design enables complementary and aligned multi-view representations across structure, comparison, and narrative. In addition, we introduce a dedicated evaluation framework that systematically assesses generated surveys from multiple dimensions, including structural quality, comparative completeness, and citation fidelity. Through large-scale experiments on 76 computer science topics, we demonstrate that MVSS significantly outperforms existing methods in survey organization and evidence grounding, and achieves performance comparable to expert-written surveys across multiple evaluation metrics.

cs.CL↗

arXiv2026

Difference Feedback: Generating Multimodal Process-Level Supervision for VLM Reinforcement Learning

Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the linkage between visual evidence and intermediate steps and often causing unstable optimization and visual hallucinations. We propose Differential Feedback, which automatically constructs token/step-level supervision masks by repairing erroneous reasoning trajectories, explicitly marking the key positions that require correction. Without costly large-scale step-by-step human annotations, our method enables process-level visual alignment and can be seamlessly integrated into existing GRPO-like frameworks. Experiments on multimodal reasoning benchmarks including MMMStar and MathVista show an average 3% improvement under matched compute budgets. Our approach offers an effective, low-cost solution for accurate vision--reasoning process alignment.

cs.CV↗

arXiv2026

MetaWorld-X: Hierarchical World Modeling via VLM-Orchestrated Experts for Humanoid Loco-Manipulation

Learning natural, stable, and compositionally generalizable whole-body control policies for humanoid robots performing simultaneous locomotion and manipulation (loco-manipulation) remains a fundamental challenge in robotics. Existing reinforcement learning approaches typically rely on a single monolithic policy to acquire multiple skills, which often leads to cross-skill gradient interference and motion pattern conflicts in high-degree-of-freedom systems. As a result, generated behaviors frequently exhibit unnatural movements, limited stability, and poor generalization to complex task compositions. To address these limitations, we propose MetaWorld-X, a hierarchical world model framework for humanoid control. Guided by a divide-and-conquer principle, our method decomposes complex control problems into a set of specialized expert policies (Specialized Expert Policies, SEP). Each expert is trained under human motion priors through imitation-constrained reinforcement learning, introducing biomechanically consistent inductive biases that ensure natural and physically plausible motion generation. Building upon this foundation, we further develop an Intelligent Routing Mechanism (IRM) supervised by a Vision-Language Model (VLM), enabling semantic-driven expert composition. The VLM-guided router dynamically integrates expert policies according to high-level task semantics, facilitating compositional generalization and adaptive execution in multi-stage loco-manipulation tasks.

cs.RO↗

arXiv2026

Order Is Not Layout: Order-to-Space Bias in Image Generation

We study a systematic bias in modern image generation models: the mention order of entities in text spuriously determines spatial layout and entity--role binding. We term this phenomenon Order-to-Space Bias (OTS) and show that it arises in both text-to-image and image-to-image generation, often overriding grounded cues and causing incorrect layouts or swapped assignments. To quantify OTS, we introduce OTS-Bench, which isolates order effects with paired prompts differing only in entity order and evaluates models along two dimensions: homogenization and correctness. Experiments show that Order-to-Space Bias (OTS) is widespread in modern image generation models, and provide evidence that it is primarily data-driven and manifests during the early stages of layout formation. Motivated by this insight, we show that both targeted fine-tuning and early-stage intervention strategies can substantially reduce OTS, while preserving generation quality.

cs.CL↗

arXiv2026

Learning with Challenges: Adaptive Difficulty-Aware Data Generation for Mobile GUI Agent Training

Large-scale, high-quality interaction trajectories are essential for advancing mobile Graphical User Interface (GUI) agents. While existing methods typically rely on labor-intensive human demonstrations or automated model exploration to generate GUI trajectories, they lack fine-grained control over task difficulty. This fundamentally restricts learning effectiveness due to the mismatch between the training difficulty and the agent's capabilities. Inspired by how humans acquire skills through progressively challenging tasks, we propose MobileGen, a novel data generation framework that adaptively aligns training difficulty with the GUI agent's capability frontier. Specifically, MobileGen explicitly decouples task difficulty into structural (e.g., trajectory length) and semantic (e.g., task goal) dimensions. It then iteratively evaluates the agent on a curated prior dataset to construct a systematic profile of its capability frontier across these two dimensions. With this profile, the probability distribution of task difficulty is adaptively computed, from which the target difficulty for the next round of training can be sampled. Guided by the sampled difficulty, a multi-agent controllable generator is finally used to synthesize high-quality interaction trajectories along with corresponding task instructions. Extensive experiments show that MobileGen consistently outperforms existing data generation methods by improving the average performance of GUI agents by 1.57 times across multiple challenging benchmarks. This highlights the importance of capability-aligned data generation for effective mobile GUI agent training.

cs.AI↗

arXiv2025

Distributed Fault-Tolerant Control for Heterogeneous MAS with Prescribed Performance under Communication Failures

This paper presents a novel approach employing prescribed performance control to address the distributed fault-tolerant formation control problem in a heterogeneous UAV-UGV cooperative system under a directed interaction topology and communication link failures. The proposed distributed fault-tolerant control scheme enables UAVs to accurately track a virtual leader's trajectory and achieve the desired formation, while ensuring UGVs converge within the convex hull formed by leader UAVs. By accounting for differences in system parameters and state dimensions between UAVs and UGVs, the method leverages performance functions to guarantee predefined transient and steady-state behavior. Additionally, a variable prescribed performance boundary control strategy with an adaptive learning rate is introduced to tackle actuator saturation, ensuring reliable formation tracking in real-world scenarios. Simulation results demonstrate the effectiveness and robustness of the proposed approach.

eess.SY↗

arXiv2025

Limit cycles bifurcating from the quasi-homogeneous polynomial centers of weight-degree 2 under non-smooth perturbations

We investigate the maximum number of limit cycles bifurcating from the period annulus of a family of cubic polynomial differential centers when it is perturbed inside the class of all cubic piecewise smooth polynomials. The family considered is the unique family of weight-homogeneous polynomial differential systems of weight-degree 2 with a center. When the switching line is $x=0$ or $y=0$, we obtain the sharp bounds of the number of limit cycles for the perturbed systems by using the first order averaging method. Our results indicate that non-smooth systems can have more limit cycles than smooth ones, and the switching lines play an important role in the dynamics of non-smooth systems.

math.DS↗

arXiv2025

SGDRC: Software-Defined Dynamic Resource Control for Concurrent DNN Inference on NVIDIA GPUs

Cloud service providers heavily colocate high-priority, latency-sensitive (LS), and low-priority, best-effort (BE) DNN inference services on the same GPU to improve resource utilization in data centers. Among the critical shared GPU resources, there has been very limited analysis on the dynamic allocation of compute units and VRAM bandwidth, mainly for two reasons: (1) The native GPU resource management solutions are either hardware-specific, or unable to dynamically allocate resources to different tenants, or both; (2) NVIDIA doesn't expose interfaces for VRAM bandwidth allocation, and the software stack and VRAM channel architectures are black-box, both of which limit the software-level resource management. These drive prior work to design either conservative sharing policies detrimental to throughput, or static resource partitioning only applicable to a few GPU models. To bridge this gap, this paper proposes SGDRC, a fully software-defined dynamic VRAM bandwidth and compute unit management solution for concurrent DNN inference services. SGDRC aims at guaranteeing service quality, maximizing the overall throughput, and providing general applicability to NVIDIA GPUs. SGDRC first reveals a general VRAM channel hash mapping architecture of NVIDIA GPUs through comprehensive reverse engineering and eliminates VRAM channel conflicts using software-level cache coloring. SGDRC applies bimodal tensors and tidal SM masking to dynamically allocate VRAM bandwidth and compute units, and guides the allocation of resources based on offline profiling. We evaluate 11 mainstream DNNs with real-world workloads on two NVIDIA GPUs. The results show that compared with the state-of-the-art GPU sharing solutions, SGDRC achieves the highest SLO attainment rates (99.0% on average), and improves overall throughput by up to 1.47x and BE job throughput by up to 2.36x.

cs.DC↗