arXiv subjects

Xin Zhang

Publications and source records attributed to Xin Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2026

Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO

This paper introduces Actor as Its Own Critic, a unified reinforcement learning framework, Cycle Group Relative Policy Optimization (CycleGRPO), that jointly optimizes region understanding and localization for Multimodal Large Language Models (MLLMs). Unlike existing separate pipelines, we leverage the inherent duality between the two tasks to construct a self-evaluating reinforcement learning paradigm: "region $\to$ text $\to$ region''. Specifically, a single MLLM first acts as the actor to generate region captions, then immediately transitions to a critic to ground its generated text back in the spatial domain. Therefore, CycleGRPO requires only region inputs, e.g., masks or bounding boxes, entirely bypassing the need for textual ground truths. A quality-aware token-level cycle-consistency reward is employed to assess the semantic discriminability of text captions via their physical localization accuracy. Empirically, built upon SAMTok, our CycleGRPO framework successfully bootstraps both capabilities simultaneously. Without any task-specific fine-tuning, the framework yields consistent performance gains across a wide range of benchmarks, including region captioning, region VQA, grounded dialogue, and referring segmentation. Overall, CycleGRPO offers a straightforward and scalable way to advance pixel-level capabilities in MLLMs. Code and models are released at https://github.com/devinxzhang/CycleGRPO.

cs.CV↗

arXiv2026

SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams

LLM agents increasingly self-improve by writing and reusing textual skills, kept either as one global document or as a flat pool of per-task entries, though most of the evidence comes from domains with structurally similar tasks. On long-horizon workloads where each task demands a different solution, the two forms fail in opposite ways: the document collapses into generic discipline, while the pool inflates and its entries stay bound to the instance that wrote them. We argue the missing unit of reuse is the solving procedure shared by a cluster of related tasks, and build SkillGLoW (Global-Local Weave) around it: the local skills a task writes from its own execution are aggregated into procedural families and compressed into de-instantiated global priors, while the instance detail they hold is regenerated per task rather than stored; a commit gate admits a prior only when real execution shows it does not degrade the deployed library. Across four benchmarks (mathematical reasoning, terminal automation, software repair, and embodied control) and three models, the priors gain 17.2 points (hard) over the no-skill baseline on average, with positive gains in all 12 continual-improvement runs, and 18.0 with local regeneration, while the library holds one prior per procedural family, 3.6x more compact than the per-task pool. Under the same protocol GLoW leads a published single-document optimizer on 15 of 21 cells. Unmodified, the library lifts success on unseen ALFWorld tasks from 73.9% to 83.9%, evidence that what transfers is procedure rather than task memory.

cs.AI↗

arXiv2026

Universal fingerprint of topological defect cores

Topological defects are ubiquitous in physics, arising from condensed matter physics to the early universe. Although there exist many universal scaling laws for correlations between topological defects, such as Porod scaling, the fingerprint of topological defect cores has remained largely unexplored. Here, we discover a universal scaling law in the region $k>1/ξ$, where $ξ$ is the healing length of the topological defects, taking the scaling of the form factor $S_f \propto k^{-(d+p+2)}$, where $d$ is the spatial dimension and $p$ is the defect codimension. We analytically prove that this exponent originates from a universal V-shaped cusp at the defect core and is independent of the underlying system and dynamics. Numerical simulations verify this scaling law in four typical frameworks: the time-dependent Ginzburg-Landau and Gross-Pitaevskii equations in the weak-coupling regime, the gauge/gravity duality model in the strong-coupling regime, and the Klein-Gordon equation in the Friedmann-Robertson-Walker background in cosmology. Our work provides a new probe for studying topological defects in systems ranging from superconductors to cosmological phase transitions.

hep-th↗

arXiv2026

BiMTokenizer: Preserving Semantic-Acoustic Balance in Low-Bitrate Speech Tokenization via Bidirectional State-Space Modeling

Speech codecs serve as bridges between continuous speech signals and large language models, yet face an inherent conflict between acoustic fidelity and semantic preservation. To mitigate this conflict, recent works increasingly adopt dual-tower architectures to decouple semantic and acoustic modeling with separate encoders. However, these dual-tower designs incur substantial architectural overhead. To avoid such complexity, we revisit the single-tower paradigm and propose BiMTokenizer, a low-bitrate speech codec (around 1.1 kbps) combining a bidirectional state-space backbone with Residual Spherical Leech Quantization (RSLQ). The bidirectional backbone strengthens temporal modeling, while RSLQ offers a fixed, well-separated lattice bottleneck for robust semantic and acoustic tokenization without learned-codebook collapse. Experiments show that BiMTokenizer achieves superior acoustic reconstruction and the lowest WER among low-bitrate codec baselines across both clean and noisy environments, while using less than half the parameters of recent dual-tower baselines. Furthermore, its robust semantic representations yield strong performance on downstream speech understanding tasks, confirming that a well-designed single-tower codec can preserve the semantic-acoustic balance at low bitrates. The code and model weights are available at https://github.com/ZhangXinWhut/BiMTokenizer.

cs.SD↗

arXiv2026

X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests

Competitive programming remains challenging for code LLMs. Despite recent progress, many training pipelines still depend on scarce real-world data, raising concerns about scalability and near-duplicate benchmark contamination. In this paper, we examine whether synthetic training artifacts can support the complete SFT-to-RL cycle for competitive programming: no real-world tasks, solutions, or test cases are directly used for post-training. To this end, we synthesize tasks, verified solutions, and reliable test cases that serve as reward signals for reinforcement learning. To improve reward reliability, we introduce a dual-verification strategy that reduces noise in both selected solutions and test outputs. Using this high-quality data, we train the X-Coder model series. X-Coder-14B achieves 67.5\% avg@8 on LiveCodeBench v5 and 63.4\% on v6, outperforming its base model by over 40 points. Further analysis provides practical insights into synthetic post-training, highlighting the value of diverse tasks, verified long-CoT supervision, and code-centric reinforcement. Our data and models are released at https://github.com/JieWu02/X-Coder

cs.CL↗

arXiv2026

Three-band dark-siren cosmology with intermediate mass black hole binaries: Synergy of Taiji, LGWA, and the Einstein Telescope

Gravitational-wave (GW) dark sirens provide an independent probe of the cosmic expansion history. Their cosmological constraining power, however, depends critically on precise luminosity-distance measurements and sky localizations for cross-matching with galaxy catalogs. Multiband GW observations can track GW events across different frequency bands and thus improve both. Motivated by this, we forecast the cosmological potential of intermediate-mass black hole binaries (IMBHBs) observed by a three-band GW detector network composed of Taiji (TJ), the Lunar Gravitational-wave Antenna (LGWA), and the Einstein Telescope (ET). We simulate detectable IMBHB populations and analyze them with a hierarchical Bayesian dark-siren framework that includes galaxy-catalog completeness and redshift uncertainties. We find that the TJ-LGWA-ET network outperforms all two-detector configurations considered here. In the $Λ$CDM model, it constrains the Hubble constant and matter density to $\sim 0.12\%$ and $\sim 0.6\%$, respectively. In the $w$CDM model, a 4-year dark-siren sample alone constrains the dark-energy equation-of-state parameter $w$ to $\sim 2.7\%$. Adding baryon acoustic oscillation (BAO) and Type Ia supernova (SNe Ia) data improves the $w$ constraint to $\sim 2.1\%$, slightly better than that from the current CMB+BAO+SNe Ia combination. We also show that the final constraints remain sensitive to IMBHB population assumptions and galaxy-catalog limitations, which highlights the need for deep galaxy surveys with precise redshift measurements.

astro-ph.CO↗

arXiv2026

CAER: Causal Action Effect Reweighting for World Model Training

World models are becoming core infrastructure for embodied intelligence, with action-conditioned video generation providing controllable predictions of how scenes evolve after agent interventions. Yet existing models are commonly trained with space-time-uniform mean squared error, allowing abundant background tokens to dominate the gradient while sparse interaction dynamics remain under-optimized; such uniform fitting rewards reconstructing appearance rather than learning how actions change the world. We introduce Causal Action Effect Reweighting (CAER), a general training paradigm that redistributes supervision toward the tokens whose predicted future is causally affected by the action. CAER contrasts the model's own predictions with and without action conditioning to localize these tokens online, then normalizes the resulting effect map into a weight that preserves the total coefficient mass and changes only where it is spent. This online signal requires no external annotations or offline preprocessing, avoids additional data-processing time, and scales naturally with model and dataset size. Experiments across heterogeneous action-conditioned world-model tasks show that CAER converges to better solutions than uniform MSE training, with consistent improvements in the physical consistency, controllability, and visual quality of generated videos.

cs.AI↗

arXiv2026

IMPACT: Attention Is the Interaction Map for Scalable Interaction-Aware World Model Training

World models have made remarkable progress in action-conditioned future prediction for embodied agents, yet still struggle to model physically plausible interactions. Existing approaches address this limitation by constraining the generation process with external representations encoding motion, geometry, or semantics. Obtaining these spatiotemporally dense representations typically requires auxiliary estimators or manual annotations, limiting training scalability. We instead revisit the training objective and identify a supervision-allocation mismatch under the globally averaged mean squared error (MSE) denoising objective: prevalent static content dominates the optimization signal, leaving sparse dynamic-object regions critical to interaction generation disproportionately under-supervised. Motivated by this observation, we introduce IMPACT, a scalable Interaction-aware Model training framework with Prior-guided Attention Calibration and Targeting. IMPACT uses cross-attention associated with manipulated-object tokens as an internal spatiotemporal prior for action-conditioned changes. It samples candidate regions from this prior, calibrates them with detached local prediction errors to construct an interaction map, and uses the map to reweight denoising supervision, requiring neither external representations nor inference-time modifications. Extensive experiments on robot-arm and human-hand manipulation, spanning diverse control modalities and DiT backbones, show that IMPACT consistently outperforms the corresponding MSE-trained baselines, improving interaction fidelity, physical plausibility, and visual quality.

cs.AI↗

arXiv2026

JITterFlip: Uncovering Fault Attack Surfaces in JIT-Compiled LLM Serving

LLMs are widely deployed through cloud-hosted inference services, where Just-in-Time (JIT) compilation is used to reduce recurring framework and GPU-launch overhead. JIT serving introduces a host-side control plane that selects compiled artifacts and orchestrates their execution on the GPU. Meanwhile, the shared cloud setting has motivated a growing body of bit-flip attacks (BFAs) against LLM/DNN inference. Most existing BFAs target model parameters or weights and require model-specific knowledge. A smaller body of work reduces this dependency by faulting executable code, yet still corrupts code that directly implements model computation, limiting their attack effect to inference depletion. We present JITterFlip, the first BFA targeting the host-side JIT serving control plane of GPU-based LLM inference. By faulting CPU-resident serving decisions rather than model computation, JITterFlip enables both gibberish output generation and a correct-output sponge attack. To identify exploitable targets in a large JIT compiler stack, JITterFlip develops a decision-guided fault-vulnerable code analysis. Across four text and multimodal LLM workloads, the identified vulnerable code faults exhibit cross-model transferability, produce gibberish outputs with PPL ratios of $15.45\times$ to $2.48{\times}10^{6}\times$, and demonstrate correct-output sponge attacks with latency amplification of $2.03\times$ to $181.90\times$. JITterFlip also bypasses recent BFA defenses for LLMs while retaining both attack effects. Last, we demonstrate end-to-end Rowhammer attacks across four LLMs: a single bit flip in CPU-resident branch code propagates across the CPU-GPU boundary to disrupt GPU-executed inference without direct access to GPU memory, reaching up to $7.23{\times}10^{6}\times$ PPL amplification or $124.97\times$ latency amplification while preserving the exact generated output.

cs.CR↗

arXiv2026

DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Drifting

Conventional flow-based vision-language-action (VLA) models support expressive continuous action generation but rely on multi-step refinement to produce each action chunk, increasing latency in online robot control. To address this issue, we introduce DriftingVLA, a native one-step VLA that generates a complete action chunk with a single action-expert forward pass. Rather than learning a flow field that requires iterative integration at inference, DriftingVLA uses a distribution-drifting objective to learn a direct noise-to-action-chunk mapping for one-step deployment. Since robot action dimensions carry distinct control semantics and distributional characteristics, we further introduce Per-Dimension Temporal Drifting (PDTD). PDTD treats the complete temporal trajectory of each action dimension as a separate drifting unit, enabling finer-grained modeling and shaping of dimension-specific action distributions. This per-dimension decomposition applies only to the training objective; the shared VLA model still generates the complete action chunk jointly, thereby preserving cross-dimensional dependencies. DriftingVLA achieves 98.32% success on LIBERO, 81.09% on RoboTwin 2.0, and 77.67% across six real-world single- and dual-arm tasks, outperforming the evaluated multi-step flow policy and one-step VLA baselines. Native one-step deployment also delivers a 3.36-fold speedup in action-chunk generation, eliminating iterative refinement without sacrificing control performance.

cs.RO↗

arXiv2026

DensityKV: Density-Guided KV Cache Compression for Long Video Generation

Autoregressive video diffusion models enable streaming generation through sliding-window attention, but each generated block is conditioned on previously generated content, causing appearance and motion errors to propagate recursively over time. Historical key-value (KV) memory preserves earlier subject and scene states and helps maintain long-horizon consistency. However, retaining every generated state creates a historical archive that grows continuously with the rollout, while recurrent states repeatedly add redundant coverage. To address this problem, we propose DensityKV, a training-free historical KV bank management strategy. DensityKV maintains a separate token-level KV bank for each attention head and measures local redundancy among the post-RoPE keys that directly parameterize attention routing using Soft-Riesz density. By constraining neighborhood-density growth after states enter the bank, DensityKV limits repeated historical accumulation while preserving coherent states from each completed generation block. Experiments across three autoregressive video generation backbones and multiple generation lengths show that, at the same upper bound on historical KV capacity, DensityKV improves long-horizon consistency and generation stability while keeping persistent historical storage bounded independently of rollout length.

cs.CV↗

arXiv2026

Updated constraints on interacting dark energy: A comprehensive analysis using multiple CMB probes, DESI DR2, and supernovae observations

Recent DESI baryon acoustic oscillation (BAO) measurements, combined with Planck cosmic microwave background (CMB) data and DESY5 type Ia supernova (SN) data, indicate a significant deviation from $Λ$CDM, which seems to suggest that this deviation can be explained by an interaction between dark energy and dark matter. In this work, we perform a comprehensive analysis by utilizing the latest DESI DR2 BAO data in conjunction with CMB data from ACT, SPT, Planck, and WMAP, along with SN data from PantheonPlus and DESY5. We consider four interacting dark energy (IDE) models with different forms of the interaction term $Q$. Our analysis indicates that CMB experiments other than Planck enhance the evidence for an interaction in the IDE models with $Q \propto ρ_{\rm de}$. In particular, when using the SPT+DESI+DESY5 data, the IDE model with $Q = βH_0 ρ_{\rm de}$ gives $β= -0.4170 \pm 0.1220$, with a deviation from zero reaching $3.4σ$ level. When replacing DESY5 with PantheonPlus, this deviation weakens to $2.1σ$ level, but remains relatively significant. Furthermore, the Bayes factors of the IDE model with $Q = βH_0 ρ_{\rm de}$ are positive in all cases, providing a moderate-to-strong preference over $Λ$CDM. Overall, our comprehensive analysis clearly suggests that the IDE models with $Q \propto ρ_{\rm de}$ (especially, $Q = βH_0 ρ_{\rm de}$) provide strong evidence supporting the existence of interaction and are more preferred by the current cosmological data.

astro-ph.CO↗

arXiv2026

Resolving the Hubble Tension in the Early Dark Energy Framework with JWST and DESI Data

In the JWST and DESI era, the JWST high-redshift galaxy observations and DESI baryon acoustic oscillation (BAO) measurements severely challenge the standard $Λ$CDM model, while the $H_0$ tension becomes increasingly prominent. In this work, we investigate the capability of the early dark energy (EDE) model to alleviate the $H_0$ tension utilizing cosmic microwave background data from Planck, ACT, and SPT, BAO data from DESI, and ultraviolet luminosity function observations from the JWST. Within the canonical axion EDE framework, the CMB+DESI+JWST data significantly increase the $H_0$ value to $71.58\pm1.05\,\mathrm{km\,s^{-1}\,Mpc^{-1}}$, alleviating the $H_0$ tension to the $1.0σ$ level. Simultaneously, this model improves the fit to the JWST data and exhibits statistical performance significantly better than the $Λ$CDM model, with $Δχ^2_{\mathrm{tot}} = -18.26$ and $Δ\mathrm{DIC} = -11.89$. Our results highlight the complementary advantages of JWST high-redshift galaxy data alongside early- and late-time observations in testing EDE and alleviating the $H_0$ tension.

astro-ph.CO↗

arXiv2026

LDAC-Net: A Learnable Multi-Lag Differencing Attention-Convolution Network for Drift-Robust Recognition with Low-Cost MOX Gas Sensors

Portable electronic-nose systems based on low-cost metal-oxide (MOX) gas sensors offer a practical solution for gas and odour recognition, but their signals are affected by slow chemical transients, drifting sensor offsets, scale variation, and cross-channel correlations. Existing pipelines commonly use fixed first-order temporal differencing (FOTD), which requires a manually selected lag and may discard useful response information. We propose LDAC-Net, an end-to-end learnable multi-lag differencing attention-convolution network that operates directly on multi-channel MOX signals. Its learnable differential feature enhancement front-end combines window-conditioned statistical affine normalisation, which compensates for window-specific offset and scale variation, with learnable multi-lag differencing, which weights and combines temporal differences across multiple lags. A compact attention-convolution backbone subsequently models local transients and longer-range temporal dependencies. On the 50-class SmellNet-Base task, LDAC-Net achieves 68.2% top-1 accuracy, exceeding the best FOTD-preprocessed comparison model by approximately 14 percentage points and the raw-input Transformer by more than 30 points. Ablation studies confirm the contributions of both proposed components. The representation also transfers to SmellNet-Mixtures, improving accuracy from 45.4% to 50.5%, and generalises to the 62-channel eNose-Drift benchmark under strong long-term drift, achieving 70.6% top-1 accuracy and 69.6% macro-F1. These results outperform the best comparison model with dataset-retuned FOTD preprocessing by 8.0 and 3.0 points, respectively, demonstrating that learnable, sensor-aware preprocessing is more effective than fixed handcrafted differencing for low-cost MOX gas-sensor recognition.

cs.LG↗

arXiv2026

Unveiling the spectral morphological division of fast radio bursts with CHIME/FRB Catalog 2

Fast radio bursts (FRBs) are commonly classified into repeating and apparently nonrepeating sources, yet whether this distinction reflects intrinsically different physical populations remains uncertain. Using the Second CHIME/FRB Catalog, we apply an unsupervised machine learning framework combining Uniform Manifold Approximation and Projection (UMAP) with density-based clustering to investigate the intrinsic structure of the FRB population in a multi-dimensional parameter space. We find that FRBs are primarily separated into two robust clusters dominated by spectral morphology. One cluster is characterized by narrowband emission and longer durations, while the other exhibits relatively broadband spectra and shorter burst timescales. This classification scheme achieves a recall of 0.94 for known repeaters. Within the repeating population, we further identify a stable subclass of atypical repeaters that are broadband, shorter in duration, and more luminous, resembling nonrepeating bursts. Furthermore, broadband nonrepeaters exhibit systematically higher dispersion measures (by approximately 200 $\text{pc cm}^{-3}$) and isotropic luminosities approximately an order of magnitude larger than those of repeating FRBs. Without invoking catastrophic progenitor scenarios, these differences are naturally explained by instrumental sensitivity limits and distance-dependent selection effects. Our results provide new statistical evidence for a physical connection between repeating and nonrepeating FRBs.

astro-ph.HE↗

arXiv2026

TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction

World Action Models (WAMs) combine future-state prediction with robot action generation, but existing approaches largely rely on visual futures. Visual prediction captures scene structure and object motion, yet provides limited supervision for force, deformation, shear, and slip during contact-rich manipulation. This creates two design requirements: tactile futures should carry meaningful physical information, and they should not become privileged cues for action generation. We present TacWAM, a mechanics-aware tactile WAM that addresses this challenge in three steps. First, a Spatially Aligned Fusion (SAF) Tactile Encoder maps tactile appearance, dense force fields, and deformation flow into a shared latent prediction space, with bilateral force and torque reconstruction preserving global contact information. Second, a tactile history encoder provides temporal context so future tactile prediction reflects how force and deformation change beyond the current tactile observation. Third, Anchor-Guided Tri-Modal (AGT) Attention separates current visual and tactile anchors, future prediction tokens, and action tokens, allowing future tactile states to supervise training without being directly read by the action branch. We evaluate TacWAM on four real-world contact-rich manipulation tasks covering fragile grasping, sustained surface contact, and dynamic in-hand manipulation. TacWAM achieves an average success rate of 75.0%, exceeding the strongest evaluated baseline by 37.5 percentage points. Staged ablations show consistent degradation when tactile history is removed and access to future prediction targets is relaxed. These results indicate that future tactile supervision can improve contact-aware action learning when combined with informative tactile representations and deployment-consistent information constraints.

cs.RO↗

arXiv2026

Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning

Answer-only reinforcement learning (RL) trains reasoning models to solve fully specified problems, but many realistic queries omit a premise needed for a unique answer. In this setting, the useful response is not always refusal: the model should ask for the missing premise, condition its answer on the unknown quantity, or abstain when no informative conditional response is available. We present \emph{Ask-Condition-Abstain Reinforcement Learning} (ACA-RL), a data-augmented RL framework for this setting. Its reasoning-graph-guided pipeline converts well-posed problems into missing-premise training instances with localized gap annotations; ACA-RL then trains on these instances with a structured reward over five observable response behaviors. We also introduce the \emph{Missing-Premise Benchmark} (MPB), a 274-instance human-verified benchmark spanning mathematical, logical, and real-world word problems. Across Qwen3 and Llama models, ACA-RL consistently improves on MPB while preserving competitive performance on well-posed reasoning tasks. Together with the released code, MPB, and training data, this work supports a new mission for NLP evaluation: measuring whether models can recognize when a task is underdetermined and handle uncertainty, not only whether they can answer fully specified questions.

cs.CL↗

arXiv2026

DPIAgent: Divide, Protocol, Isolate for Agentic Reproduction Test Generation

Reproduction test generation, producing a failing-then-passing test that captures a reported bug, is a critical step in automated software engineering. Existing agentic methods treat this as a monolithic loop, despite the task inherently comprising two subtasks of distinct nature: diagnosing the root cause and writing a fail-to-pass test. Without explicit separation, the agent faces a compound objective with underspecified intermediate goals, leading to goal drift. We propose DPIAgent, a structured agentic framework built on three principles, Divide, Protocol, Isolate (DPI), that mitigates compound-objective ambiguity and goal drift: it Divides the task into single-objective phases of defect exploration and test generation; enforces a handoff Protocol that records the diagnosis and test plan, preventing context loss; and Isolates each phase's action space by tailoring the toolset to its task, preventing irrelevant tools from misleading execution. On SWT-Bench Verified, DPIAgent outperforms seven baselines across three backbone LLMs. With DPI alone it reaches 81.76% success rate on GPT-5, the highest reported among open-source methods, gaining up to 11.88 points over the strongest baseline on GPT-5-Mini; adding test selection further raises it to 86.17%. Our analysis shows that architectural structure and backbone capability are complementary axes rather than substitutes, demonstrating DPI's generalizability across model classes.

cs.SE↗