Searcharxiv⌕ Search

arXiv subjects

Ming Xu

Publications and source records attributed to Ming Xu.

At least 19 recordsLinked to original sources

AI climate trajectories shaped by growth, power choices and decarbonization

Artificial intelligence (AI) is emerging as a major source of electricity demand, yet its operational greenhouse gas (GHG) emissions remain difficult to resolve geographically. We develop a facility-level global inventory of AI-oriented data centers and extend it to 2030 using documented expansion plans and grid-policy scenarios. Under Current Policies, emissions increase from 20.4 MtCO$_2$e in 2024 to 68.7 MtCO$_2$e in 2030, with parameter-side Monte Carlo 5th--95th percentile ranges of 19.3--21.0 and 60.8--73.9 MtCO$_2$e, respectively. Only six geographies, representing less than 3% of projected capacity, avoid rising emissions. Grid decarbonization consistent with net zero by 2050 lowers projected 2030 emissions to 48.3 MtCO$_2$e, but fossil-based behind-the-meter generation erodes this benefit. Under that scenario, the U.S. behind-the-meter emissions penalty exceeds the combined AI-data-center emissions outside the United States. These findings support coordinated capacity planning, faster access to low-carbon electricity and limits on routine fossil-based behind-the-meter supply.

physics.soc-ph↗

BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions

Task automation has been greatly empowered by the recent advances in Large Language Models (LLMs) via Python code, where the tasks ranging from software engineering development to general-purpose reasoning. While current benchmarks have shown that LLMs can solve tasks using programs like human developers, the majority of their evaluations are limited to short and self-contained algorithmic tasks or standalone function calls. Solving challenging and practical tasks requires the capability of utilizing diverse function calls as tools to efficiently implement functionalities like data analysis and web development. In addition, using multiple tools to solve a task needs compositional reasoning by accurately understanding complex instructions. Fulfilling both of these characteristics can pose a great challenge for LLMs.To assess how well LLMs can solve challenging and practical tasks via programs, we introduce BigCodeBench, a benchmark that challenges LLMs to invoke multiple function calls as tools from 139 libraries and 7 domains for 1,140 fine-grained tasks. To evaluate LLMs rigorously, each task encompasses 5.6 test cases with an average branch coverage of 99%. In addition, we propose a natural-language-oriented variant of BigCodeBench, BigCodeBench-Instruct, that automatically transforms the original docstrings into short instructions only with essential information. Our extensive evaluation of 60 LLMs shows that LLMs are not yet capable of following complex instructions to use function calls precisely, with scores up to 60%, significantly lower than the human performance of 97%. The results underscore the need for further advancements in this area.

cs.SE↗

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.

cs.SE↗

On the algebraic bipartite graphs $D(4s,q)$

Lazebnik-Ustimenko graphs $D(k,q)$ constitute a notable family of $q$-regular, edge-transitive bipartite graphs characterized by high symmetry and large girth, with wide applications in algebraic graph theory and coding theory. The precise girth of $D(k,q)$ is governed by a celebrated conjecture proposed by Füredi et al., which remains unresolved in general cases. Although prior works have validated this conjecture for several specific parameter regimes and established fundamental structural properties of graph girth, a systematic characterization of girth cycles for even-indexed subfamilies of \(D(k,q)\) is still absent. This paper focuses on the graph subclass $D(4s,q)$ and conducts structural analysis via its isomorphic bipartite model $Λ_{k,q}$. We derive an explicit necessary and sufficient condition for the existence of length-$(4s+4)$ backtrackless circuits in $Λ_{4s,q}$. Using this criterion, we completely characterize all girth cycles of $Λ_{8,q}$ and verify the Füredi-Lazebnik-Ustimenko girth conjecture for the parameter family $k=2(p^r+1)p^t-4$ over finite fields of odd characteristic $p\geq 3$ with $q=p^m>3$. The results further enrich the structural theory of symmetric large-girth bipartite graphs and extend the valid parameter range of this classic girth conjecture.

math.CO↗

Xiaomi-Lens-0 Technical Report

Multimodal large language models (MLLMs) answer questions about whole images well, yet they still struggle with fine-grained region understanding. A key reason is that text-only supervision never specifies which regions support an answer. To close this gap, we present Xiaomi-Lens-0, a 4B MLLM built on Qwen3.5 that predicts masks from its own visual representations. Specifically, a lightweight decoder combines vision-encoder patch features with the language model's mask-token states, termed visual latents, so that mask supervision reaches the shared backbone without an additional segmentation encoder. Because each latent decodes to a mask, the model can interleave reasoning with region-specific latents and thus think with visual latents, while grounded reasoning traces supervise the intermediate regions referenced during chain-of-thought. As a result, across all eight RefCOCO, RefCOCO+, and RefCOCOg splits, Xiaomi-Lens-0 gains 5.6 points on average over Qwen3.5 in referring comprehension and achieves the highest segmentation cIoU among compared models. Moreover, it surpasses Qwen3.5 across all perception benchmarks. Homepage: https://seerray-lab.github.io/Xiaomi-Lens-0

cs.CV↗

Improving Human Diving Endurance with a Field-Deployable Exoskeleton

Human endurance in underwater locomotion is fundamentally restricted by high energetic demands to overcome drag while managing a finite supply of self-contained breathing gas. Here, we present DiveMate, a field-deployable exoskeleton designed to improve human diving endurance via kick assistance in real-world underwater environments. DiveMate increases the travel distance using a given amount of breathing gas by 42.9% and extends dive duration by 54.9% through reducing the gas consumption rate. Marked reductions in muscle activation indicate decreased physiological exertion, with the net gas consumption rate decreasing by 47.0%. Changes in kinematic characteristics further contribute to powerful and efficient kicking. Successful open-water trials at depths up to 30 m demonstrated field feasibility. These results suggest that applying exoskeleton assistance is beneficial for improving human diving endurance and augmenting their ability to explore the aquatic world. This study extends the application frontier of exoskeletons and provides a potential reference for the design and assessment of future underwater assistive devices.

cs.RO↗

Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning

With massively parallel simulation, on-policy Reinforcement Learning methods such as PPO have become standard in many domains. However, learning from scratch is sample-inefficient and fails to exploit the potential existence of a suboptimal expert, such as a heuristic, a model-based controller, or a policy trained on a related task. Such an expert is often available and can guide early training, but its sub-optimality limits final performance. The challenge then becomes balancing expert guidance against learning from rewards. Existing methods set the expert's influence through a blending weight, a schedule, or an evaluation-driven curriculum. Alternatively, they adapt it with additional learned components such as critics over expert actions or auxiliary agents. However, none optimizes it using the same on-policy objective as the policy itself. We propose a method in which the learner and the expert alternate control within each training episode, and the expert's share of control is a single learnable parameter optimized jointly with the policy. The learner benefits from the expert early in training, but its share of control declines as the learner becomes more competent, until eventually vanishing completely. This leaves the learner acting alone and better than the suboptimal expert. We evaluate our method on 34 tasks across two benchmarks, spanning discrete and continuous action spaces, using both learned and model-based experts. Our method improves sample efficiency over guided and unguided baselines while requiring minimal hyperparameter variation. The expert's share decays to zero as the learner improves, vanishing when the expert is no longer useful.

cs.LG↗

Teaching a Moving Student: Rethinking the Curriculum of On-Policy Distillation

In on-policy distillation (OPD), the student determines which states receive teacher supervision. As its policy evolves, earlier response prefixes become less likely even though teacher-student disagreement on them persists. Under matched trajectory and optimization budgets, neither more queries nor more frequent rollout resampling is uniformly beneficial. Current-policy rollouts outperform initial-policy rollouts at shorter response budgets, but this ranking reverses at longer budgets. Replaying initial-policy rollouts after current-policy training improves accuracy, whereas replaying fixed recent rollouts does not reproduce the gain. We propose R-OPD, a gradient-triggered curriculum that adaptively selects when to revisit initial-student trajectories. When changes in mean gradients fall within minibatch-level variation for two consecutive comparisons, training switches from the next iteration onward to initial-policy replay. Across eight mathematics benchmarks and three training-data orders, R-OPD improves average accuracy over continued current-policy sampling by 2.25/4.44 percentage points at 16K/32K for a 0.6B student and 2.81/6.15 points for a 1.7B student. With a 30B-A3B teacher, it improves 8B accuracy by 4.05 points at 32K. At 32K, R-OPD exceeds a fixed schedule of 40 current-policy updates followed by 20 replay updates by 1.39/1.66/1.85 points for 0.6B/1.7B/8B. At the same generation cap, R-OPD also produces longer responses, suggesting that well-timed revisits help students use more of their reasoning capacity.

cs.CL↗

When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents

Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: past a critical pool size, newly added skills degrade performance instead of improving it. We formalize this capability-contamination phase transition and trace it to a structural cause: once a defective skill enters the decision context, it becomes reference material for distilling later skills, forming cross-round contamination chains. We further show the contamination is structurally irreversible: removing a source skill after the fact cannot erase the flawed reasoning its descendants have already inherited, so post-hoc rollback recovers only a small fraction of the lost performance. This makes skill admission a pre-commit necessity rather than a post-hoc fix, and motivates Verifier-as-Gatekeeper (VaG): a progressive trust hierarchy whose three heterogeneous critics - structural validity, behavioral harmlessness, and semantic consistency - filter each skill individually, coupled with a marginal-gain subset selection that removes combinatorial contamination at the top tier before skills reach the runtime context. On Terminal-Bench 2, unconditional accumulation rises to a peak and then degrades, giving back most of its gains as the pool keeps growing, and post-hoc removal of the culprit skills recovers only a small part of the drop - the empirical signature of irreversibility. In contrast, VaG improves every round, reaching 72% pass@1 with a pool roughly 5x smaller, and its frozen skill pool transfers positively to four other backbones and a second benchmark without re-evolution. Ablations confirm the three critics are complementary and mutually non-substitutable, each intercepting a largely disjoint class of harmful skills.

cs.AI↗

Generalizable Neural Reconstruction of High-Fidelity Surfaces via Sparse Volumetric Representations

Neural implicit representations have recently achieved impressive results in novel view synthesis and multi-view 3D reconstruction, yet both NeRF- and Gaussian Splatting-based methods require per-scene optimization, which makes them inefficient. Generalizable Neural Surface Reconstruction (GNSR) methods have been proposed to remove this need by learning feature representations directly predicted from input images. However, their typical reliance on dense feature volumes severely limits achievable resolution and fidelity due to prohibitive memory costs. We introduce Sparse Volumetric Reconstruction (SVRecon), a new GNSR framework that unlocks high-resolution, memory-efficient reconstruction through learned occupancy-driven sparsity, in a more effective way than earlier approaches to introducing sparsity in GNSRs. Our approach uses a nested two-stage architecture: (1) an occupancy prediction network that identifies surface-containing voxels, and (2) a high-resolution sparse volume rendering framework defined only within these occupied regions, together with specialized sparsified algorithms for ray sampling, feature aggregation, and querying. This design enables fine-grained surface reconstruction while avoiding the heavy memory footprint of dense grids. SVRecon operates at resolutions up to $512^3$ on standard 32GB hardware---substantially higher than prior generalizable methods---and delivers smoother and more precise reconstructions across diverse datasets, particularly in sparse-view settings.

cs.CV↗

Distillation as Probability Transport: Routed On-Policy Distillation

On-policy distillation (OPD) transfers teacher knowledge on student-generated trajectories, but efficient sampled objectives reduce the teacher distribution to scalar credit on individual tokens. Such credit indicates whether a token should gain or lose probability, yet leaves the corresponding redistribution unspecified. We recast OPD as teacher-guided probability transport and propose RouteOPD (Routed On-Policy Distillation), which decomposes local teacher--student disagreement into student-excess sources and teacher-deficit destinations and couples them into explicit transport pairs. RouteOPD optimizes pairwise log-odds toward jointly realizable targets obtained from a bounded teacher potential, while adapting the transport budget to the concentration of teacher demand. This formulation directs updates toward teacher-preferred destinations and controls their magnitude within a single transport operator. Experiments across four teacher--student settings and four mathematical-reasoning benchmarks demonstrate that RouteOPD consistently outperforms sampled reverse-KL OPD, with improvements accompanied by higher routing fidelity and lower background leakage. These results demonstrate the effectiveness of explicitly modeling probability transport in on-policy distillation.

cs.LG↗

ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation

Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recognition tasks, while the same compressed checkpoints can collapse on the free-form generation that deployment actually requires. Two observations trace this gap. First, greedy \textsc{pass}@$1$ nearly vanishes after compression, yet \textsc{pass}@$k$ recovers substantially under repeated sampling: useful generations are demoted, not erased. Second, the recoverable regime fails mainly through suffix repetition. Recovery should therefore train on the compressed model's own on-policy states with dense token-level supervision, which On-Policy Distillation (OPD) provides by reusing the pre-compression model as a frozen teacher. However, long on-policy rollouts spend early recovery budget on low-information repetitive suffixes, delaying loss descent. To mitigate this waste, we propose \textbf{\shortopd}, a short-to-long OPD schedule that detects teacher-confirmed repetitive suffixes, treats the surviving prefix as each rollout's effective length, and allocates future rollout budgets to the effective lengths the policy can currently use. Across math, code, and open-ended generation, \shortopd\ raises the compressed model's score to about $9\times$ its unrecovered value and $1.6$--$4.4\times$ standard recovery recipes (SFT w/o KD, KD, and SeqKD), and it matches a fixed $8192$-token rollout horizon within two points using a quarter of the training time ($8.5$ vs.\ $35.9$ hours) and $71\%$ fewer rollout tokens. We hope this recipe helps move structured pruning beyond marginal gains on perplexity and multiple-choice benchmarks, a step closer to deployment-ready generation quality.

cs.LG↗

First Observation of Fishbone-Driven Zonal Flows with Fine Reversed Structure in Tokamak Plasmas

We present the first direct experimental observation of fishbone-driven zonal flows in the core of the EAST tokamak. In contrast to the global pattern predicted by previous models and simulations based on the energetic-particle-expulsion mechanism, the observed flows exhibit a fine-scale, radially reversed structure inside the q = 1 rational surface. The flow rises faster and saturates earlier than the fishbone within a single burst, indicating that a beat-driven nonlinear process dominates the early stage rather than the energetic-particle-expulsion mechanism. Global nonlinear gyrokinetic simulations quantitatively reproduce the observed radial profile and reveal that this structure arises from the cancellation of comparable but opposite contributions from thermal ions and electrons. This cancellation mechanism is not captured in previous theoretical frameworks. These findings establish that the fishbone can generate sheared flows with a distinct radial topology, offering a promising pathway for regulating turbulence and improving core confinement.

physics.plasm-ph↗

Scalable and Differentiable Point-Cloud Registration Using Maximum Mean Discrepancy

We present MMD-Reg, a novel correspondence-free approach to point-cloud registration that is differentiable and has linear computational complexity in the number of points. We model registration as a nonlinear least-squares problem based on the Maximum Mean Discrepancy, approximated using random Fourier features. The resulting objective can be solved efficiently with standard methods such as Levenberg-Marquardt, and the solution is differentiable via the implicit function theorem. This allows MMD-Reg to be used as a differentiable optimization layer within end-to-end trainable models, supporting registration under challenging conditions such as poor initial alignment and partial overlap. We demonstrate this Neural MMD-Reg formulation by integrating the layer with a set transformer, training the resulting model in supervised and unsupervised settings, and comparing its performance against recent learning-based methods. We also evaluate standalone MMD-Reg, comparing its accuracy and scalability against widely used non-learning-based registration methods.

cs.CV↗

AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents

While Large Language Model (LLM) agents have made remarkable progress on complex reasoning, evaluating them in real-world environments remains an open problem. Existing benchmarks are largely confined to idealized simulations and fail to capture specialized domains such as advertising and marketing analytics, where tasks require multi-round interaction with professional tools and where ground-truth answers quickly become obsolete as data and platform rules evolve. To address this, we propose AD-Bench, a benchmark built from real user marketing-analysis requests on a production advertising platform. AD-Bench introduces two key designs: (i) a dynamic ground-truth pipeline that replays expert tool-call trajectories to regenerate answers consistent with the current environment, mitigating answer obsolescence; and (ii) a trajectory-aware evaluation that jointly measures end-to-end answer correctness (Pass@k) and trajectory coverage. Requests are stratified into three difficulty levels (L1-L3) to probe multi-round, multi-tool collaboration. Experiments show that the best model, Claude-Opus-4.7, attains Pass@1 = 76.9% and Pass@3 = 80.4% with 82.7% trajectory coverage overall, yet drops sharply on L3 to Pass@1 = 61.4% and Pass@3 = 65.1%, revealing that even state-of-the-art agents have substantial gaps in complex advertising analytics.

cs.CL↗

Structure-Aware Graph Multi-Task Learning for Dynamic Sparse OD Demand Prediction

Origin-Destination (OD) demand prediction is fundamental to intelligent transportation systems, yet real-world OD flows are often dynamically sparse, long-tailed, and characterized by heterogeneous zero-flow patterns. These properties make it difficult to distinguish whether an OD connection is active from how much demand it generates once activated. Many existing methods primarily treat OD prediction as a single flow regression task, which limits their ability to model low-frequency, intermittent, and long-tailed OD interactions. To address these challenges, we propose SAGMTL, a Structure-Aware Graph Multi-Task Learning framework for dynamic sparse OD demand prediction. SAGMTL decomposes OD prediction into structural state modeling and flow intensity estimation, jointly learning regional activity states, OD connection activity, and edge-level flow intensity within a unified framework. Specifically, a node-edge collaborative representation module captures regional semantics, temporal dynamics, and spatial priors through interactive node-edge updates, producing structure-aware representations for dynamic OD interactions. Based on these representations, SAGMTL estimates OD flows by jointly modeling stable demand patterns and short-term fluctuations. A multi-constraint objective further improves sparsity awareness and structural consistency. Experiments on three real-world urban mobility datasets from Beijing, Chengdu, and Nanjing show that SAGMTL achieves superior overall performance compared with state-of-the-art baselines. Further analysis demonstrates that explicitly modeling regional activity, connection states, and flow intensity improves the robustness of dynamic sparse OD demand prediction.

cs.LG↗

Continuous Cross-Domain Traffic State Prediction via Memory-Augmented Graph Liquid Time-Constant Networks

Traffic state prediction is a fundamental task in intelligent transportation systems. In practical applications, some regions suffer from limited traffic observations due to insufficient sensing infrastructure, making cross-domain knowledge transfer an important solution for data-scarce traffic prediction. However, existing cross-domain traffic prediction methods still face several limitations, including coarse-grained source-target adaptation, limited capability in handling unseen target-domain patterns, and insufficient modeling of continuous traffic dynamics under irregular or heterogeneous temporal conditions. To address these issues, this paper proposes a continuous cross-domain traffic prediction framework, termed Memory-Augmented Graph Liquid Time-Constant Network (MA-GLTC). Specifically, we first construct spatio-temporal units (STUs) to decompose traffic networks into transferable local units, enabling fine-grained knowledge alignment across domains. Then, a graph liquid time-constant network (GLTC) is developed to model graph-coupled traffic evolution in continuous time. Different from generic graph neural ODE-based models, GLTC introduces graph-coupled recurrent conductance into liquid time-constant dynamics, allowing node states to evolve with leakage, adaptive time constants, and neighborhood-aware feedback. Furthermore, a Memory-based Transfer Storage (MTS) mechanism is designed to preserve source-domain knowledge, retrieve matched traffic patterns, and update reliable target-domain patterns when unseen states emerge. Experiments on five public traffic datasets demonstrate that MA-GLTC consistently outperforms representative innerdomain and cross-domain baselines in both short-term and longterm prediction tasks. Compared with the second-best method, MA-GLTC reduces the average prediction errors by 3.02%, 0.33%, 8.92%, 10.09%, and 2.11%, respectively.

cs.LG↗

Unconventional crystallization pathway bypassing the intermediate cubic phase in phase-change superlattices

The Ge-Sb-Te (GST) superlattice phase-change material is a promising candidate for overcoming the high power-consumption of phase-change memory (PCM). However, the working mechanism of the superlattice PCM remains controversial. Partial amorphization, which is currently considered the most plausible mechanism, remains hotly debated: how does the partially amorphized GST recrystallize into its superlattice phase instead of the conventionally expected cubic phase? Here, we address this issue using large-scale molecular dynamics simulations enabled by a machine-learning interatomic potential. Starting from a partially melted GST superlattice, we demonstrate that the residual crystalline regions serve as nuclei, enabling the amorphous GST to recrystallize directly into the superlattice phase without passing through the intermediate cubic phase. Moreover, the recrystallized phase is not an ideal superlattice, but rather a structurally ordered and chemically disordered defective superlattice characterized by anti-site defects and stacking faults. The defective superlattice region is also more susceptible to melting than the defect-free superlattice, and thereby can act as the active region of the PCM device. These results help to clarify the longstanding debates concerning the mechanism of superlattice-based PCM.

cond-mat.mtrl-sci↗