arXiv subjects

Jian Xu

Publications and source records attributed to Jian Xu.

At least 19 recordsLinked to original sources

arXiv2026

AIGB-R1: Self-Evolving Generative Auto-Bidding via Hierarchical Planner-Executor Optimization

Auto-bidding plays an essential role in online advertising, automatically adjusting bids for advertisers to optimize their commercial goals. The emerging AI-Generated Bidding (AIGB) paradigm widely adopts generative modeling to optimize bidding strategies, yet suffers from the limited mode coverage of offline datasets and inadequate task-state understanding, hindering effective exploration of optimal strategies. Large Language Models (LLMs), with prior world knowledge and reasoning capabilities, offer a promising approach to overcome these limitations. However, directly applying LLMs to auto-bidding tasks faces inherent challenges in limited numerical precision, hallucinations, and inference latency. To address these limitations, we propose AIGB-R1, a hierarchical self-evolving auto-bidding framework aiming to enhance AI-Generated Bidding via LLMs' Reasoning capabilities, comprising a high-level Planner module for macro-level strategy planning and a low-level Executor module for fine-grained decision-making. Building upon this, we design an experience-driven self-evolving loop, enabling autonomous strategy exploration and optimization from accumulated experience. We adopt a two-stage pipeline of offline pre-training and post-training alignment, and build an interactive bidding simulation environment for strategy rollout. Furthermore, we propose Decoupled Group Relative Policy Optimization (D-GRPO) to achieve end-to-end optimization via advantage decoupling. Experimental results on a large-scale public dataset demonstrate the effectiveness of AIGB-R1.

cs.LG↗

arXiv2026

Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication

3D Gaussian Splatting (3DGS) enables high-fidelity and real-time 3D scene reconstruction, but scaling training to large-scale scenes requires optimizing hundreds of millions of Gaussians across multiple GPUs. Existing distributed approaches either partition scenes into isolated regions, causing global inconsistency, or rely on global Gaussian-level exchanges, which lead to substantial growth in inter-GPU communication and quickly dominate iteration time. We propose Splaxel, a communication-efficient distributed 3DGS training framework based on pixel-level local rendering and global composition. Instead of synchronizing Gaussians, each GPU renders its local subset and exchanges only partial pixel values, maintaining mathematical consistency while keeping communication cost stable as the scene size increases. Splaxel further reduces pixel-level redundancy through geometric and transmittance visibility prediction and improves GPU utilization via conflict-free camera-view consolidation. Evaluated on large-scale datasets with up to 120M Gaussians, Splaxel achieves up to 7.6$\times$ speedup over the state-of-the-art distributed 3DGS framework while preserving high reconstruction quality.

cs.DC↗

arXiv2026

BrowseFlow: Sparse Event Flow Matching for Generative User Simulation

User simulation aims to reproduce how users interact with content and products across online platforms. Recent generative approaches have enriched user simulation with behavioral history and contextual information. However, realistic browsing simulation still faces two challenges. (i) Stochastic Responses: Even with the same recommendation feed, the same user may produce different browsing responses, yielding distinct behavioral trajectories. A logged trajectory records only one such realization. (ii) Sparse Key Events: Clicks and likes provide important feedback but occur sparsely within browsing trajectories dominated by progression actions such as scrolling. Many stepwise simulators predict these actions in a dense sequence, where key events contribute relatively few training targets. To address these challenges, we propose BrowseFlow, a conditional discrete flow matching method for generative user simulation. For Sparse Key Events, BrowseFlow represents each response by its browsing extent and an ordered sequence of key events, directly modeling their counts and locations under exposure constraints. BrowseFlow learns the conditional distribution of complete browsing responses through probabilistic extent prediction and discrete flow matching over key events. Random event retention defines probability paths over partial event sequences, while transition rate matching learns stochastic insertion dynamics. For Stochastic Responses, we use the energy score, a proper scoring rule, to evaluate response fidelity and generated variability, complemented by the Wasserstein distance between key event count distributions. We further introduce TaobaoBrowse, a benchmark pairing real recommendation contexts with fine-grained browsing trajectories. Experiments across three datasets demonstrate that BrowseFlow consistently achieves the best distributional performance.

cs.IR↗

arXiv2026

RecIS: Unifying Sparse and Dense Computation for Efficient Recommendation Training

Modern recommender models scale sparse representations and dense computation together. They process thousands of heterogeneous feature fields, long user-behavior sequences, and trillion-scale Embedding parameters, while their dense networks increasingly use large Transformer architectures. The resulting execution mismatch creates fine-grained operations within stages, load imbalance and synchronization delays across devices, and GPU resource bubbles between stages. As models grow, these costs become a primary limit to scalable recommender training. Although existing systems improve Embedding caching and data prefetching, these inefficiencies still coexist in the GPU-centric workloads we study and jointly limit end-to-end throughput. We present RecIS, a unified framework for GPU-centric recommender training. RecIS treats the complete path from input features to dense computation as one optimization target and coordinates three complementary mechanisms. First, adaptive fusion combines fragmented feature transformations with vectorized memory access. Second, a GPU Embedding engine uses hash-based sharding and hierarchical communication to balance request placement and eliminate redundant transfers; it also specializes aggregation for forward and backward index structures. Third, a multistage pipeline overlaps input preparation for future iterations with dense computation in the current iteration. Together, these mechanisms reorganize a fragmented sparse front end into a dataflow that continuously feeds dense computation. We evaluate RecIS on representative industrial recommender models across distributed training platforms. Compared with PICASSO and TorchRec, RecIS reaches up to $2.62\times$ and $1.15\times$ their throughput, respectively, while reducing step latency by up to 61.5\% and 12.9\%. RecIS provides an efficient and scalable training system for large recommender models.

cs.DC↗

arXiv2026

The Ineliminable Anchor: Human Judgment as a Structural Requirement of Autonomous Artificial Intelligence Systems

As artificial intelligence (AI) agents carry out longer chains of tasks, oversight must establish whether their behavior still serves an authorized goal. Here, we introduce the anchor: the point at which reference information and human-authorized standards enter an autonomous system. We argue that oversight design should first identify the reference needed to assess goal drift and whether the system's internal record can supply it, then decide who checks and how often, and finally specify who may revise the goal. Goal drift can be impossible to certify from a system's internal record. The missing reference must come from outside that record. Combining a reliability model of checkpoint spacing with evidence from training, execution, and multi-agent coordination, we develop a task taxonomy to guide anchor placement and decisions about which checks to automate. For AI systems that serve human purposes, human judgment is an ineliminable structural requirement in authorizing and revising the purposes and standards that govern autonomous operation, even when routine checking and execution are automated.

cs.CY↗

arXiv2026

Where Should the Evaluation Budget Go in LLM-Driven Agent Scaffold Evolution?

Large language model (LLM)-driven agent scaffold evolution improves agent workflows through iterative candidate generation and evaluation. Evaluation both guides subsequent search and determines the final scaffold, but evaluating every candidate on the full task set incurs substantial execution costs. We investigate how evaluation budgets can be allocated across these two roles. Our experiments show that sparse feedback can sustain productive evolution, while additional targeted evaluation improves final selection. Replay analyses further show that shared informative items and a common scoring reference support comparisons among closely matched candidates. Motivated by these findings, we propose \method, an evaluation allocation framework that combines sparse search-time feedback with targeted final confirmation. A short fully evaluated warm-up establishes a shared informative core and calibrates a response model whose item parameters remain fixed during search. After search, \method refits the model and applies paired successive halving, reusing accumulated observations and executing only missing evaluations. Across four benchmarks and two evolution frameworks, \method achieves higher mean performance than full evaluation in most settings while using approximately half as many evaluation cells.

cs.LG↗

arXiv2026

LLM-Auction: Generative Auction towards LLM-Native Advertising

The commercialization of LLM applications is the next frontier in online advertising, with LLM-native advertising emerging as a promising paradigm by integrating ads into LLM-generated content. However, classic mechanisms are no longer applicable in this setting where the auction object is shifted from discrete ad slots to distributions over LLM outputs, and existing methods are impractical in industrial scenarios due to ignored externalities or high inference costs. To address these issues, we propose LLM-Auction, the first learning-based generative auction mechanism that integrates auction and generation. By formulating the allocation as preference alignment between LLM outputs and a mechanism objective that balances advertisers' value and user experience, we optimize the LLMs to inherently model allocation externalities without extra inference cost. Theoretically, we identify the allocation monotonicity and continuity of the optimal allocation rule of LLM-Auction, and prove that a simple first-price payment rule exhibits favorable incentive properties under this allocation rule. Furthermore, we build an LLM-as-a-judge simulation environment for quantitative evaluation, and experiments demonstrate that LLM-Auction achieves the state-of-the-art allocation efficiency while approximately satisfying key mechanism properties.

cs.GT↗

arXiv2026

ClunoGS: Compact Language 3D Gaussian Splatting via Unified Optimization

Language 3D Gaussian Splatting enables open-vocabulary scene understanding by associating Gaussian primitives with language features. These semantic attributes increase model storage, while most existing 3DGS compression methods are designed mainly to preserve RGB rendering quality. One straightforward approach is to apply sparsification and quantization sequentially. However, pruning based only on rendering quality can remove Gaussians that have small RGB contributions but are important for semantic prediction. Once removed, their semantic information cannot be recovered by later quantization. We propose ClunoGS, a compact framework for Language 3DGS that combines semantics-aware Gaussian sparsification and vector quantization in a unified constrained objective. Semantic supervision is used during sparsification, and the objective jointly considers rendering quality, semantic accuracy, and compactness. We optimize the unified objective with alternating primal, sparsification, quantization, and dual updates. We evaluate ClunoGS on open-vocabulary localization and segmentation using the LERF and ScanNet-10 benchmarks. Under aggressive compression, our unified, semantics-aware formulation substantially alleviates the degradation of semantic representations caused by sequential compression and semantics-agnostic Gaussian sparsification. Ablations further show that jointly coordinating sparsification and quantization better preserves semantic accuracy than applying them independently.

cs.CV↗

arXiv2026

Learning Deployable Causal Action Geometry under Temporal Non-Stationarity

Learning a response law for continuous decisions from observational time series is central to many real-world decision systems, yet temporal non-stationarity poses a fundamental challenge: as outcomes drift over time, naively pooled models can conflate action effects with shifting baselines and even reverse action rankings. Even when the one-step response is identifiable, unrestricted cross-time generalization remains fundamentally ill-posed. We therefore seek the part of the response that remains stable for decisions even when outcome levels do not. We propose deployable causal action geometry: the action-response shape that remains after anchoring away action-independent level shifts on a selected link scale and profiling out positive amplitude variation. Building on this target, we develop a two-stage orthogonal estimator that first obtains cross-fitted pilot estimates of anchored responses and then performs honest profiled selection over link, representation, and shape classes. The resulting estimator admits oracle guarantees for the restricted target and, under approximate persistence, produces decision rules that remain near optimal in future periods. Experiments on synthetic data and Dominick's support the proposed target and its transfer behavior. In a randomized Taobao A/B test, the deployed system improves GMV and purchase counts by $1.16\%$ and $1.70\%$.

cs.LG↗

arXiv2026

AIPOCH Open-Science: An Open-Source AI Research Workbench with Reproducible .science Packages

AI-assisted research leaves instructions, computations, artifact revisions and checks whose relationships matter when another researcher receives the work. We present AIPOCH Open-Science, an open-source research workbench with portable .science session packages, and specify an exchange contract for these recorded relationships. Version and assessment targets remain attributable while receiving-workspace identifiers can be remapped, eligible contents can be omitted explicitly, and imported history remains separate from a writable fork. A controlled session tested an incorrect first version, a reviewed correction, an unreviewed revision and a planned but unexecuted step. We compared complete and partial exports with source records extracted independently of the exporter, then inspected imports into separate projects within the same installation. Both conditions retained the tested version and review associations, kept the unreviewed revision distinct from earlier assessments and represented excluded content as unavailable. A documentation-rich ordinary directory also supplied evidence for all seven static inspection questions. A separate registry case connected a table to its recorded task, execution and review; offline execution of its retained script and fixed input reproduced two saved CSV tables byte for byte. The study contributes an implemented exchange contract and a controlled examination of its preservation rules, content-selection constraints and interpretation boundaries.

cs.SE↗

arXiv2026

EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs

Effective traffic signal control (TSC) requires policies that respond to changing traffic demand and network conditions while meeting different control objectives. However, adapting existing strategies often involves repeated manual design and adjustment, making it difficult to systematically explore better control rules for a target network. Large language models (LLMs) can automate this process, but directly using them to select signal phases leaves decision rules embedded in black-box models and incurs recurring inference costs and latency. This paper formulates TSC as a modular program design problem and proposes EvoSignal, an LLM-guided evolutionary framework using traffic knowledge and performance feedback. The modular representation separates traffic feature extraction, local phase prioritization, and optional network-based priority adjustment. Starting from several established strategies, EvoSignal improves programs through feedback on congestion and signal operation, retaining strategies with different performance trade-offs. The resulting programs operate without online LLM inference. Simulation experiments across five scenarios on two real-world road networks show that the selected default EvoSignal program reduces waiting time by 16.8--49.2\% relative to the lowest waiting time achieved by the 20 conventional, reinforcement learning-based, and LLM-based baselines in each scenario. A program prioritizing travel time and queue length outperforms all 20 baselines on all three metrics in the search scenario and remains among the top three on each metric when transferred unchanged to the other four scenarios. These findings support automated design of inspectable control programs that transfer across the evaluated road networks and traffic demands. Code is available at https://github.com/georgewanglz2019/EvoSignal.

cs.LG↗

arXiv2026

On the Approximation Complexity of Matrix Product Operator (MPO) Born Machines

Matrix product operator Born machines (MPO-BMs) are tractable tensor-network models for probabilistic modeling, yet their approximation capabilities remain poorly understood in theory. In this paper, we characterize these capabilities from both negative and positive perspectives. As a negative result, we prove that constructing a polynomial-bond MPO-BM approximation to an arbitrary continuous target with bounded KL error is NP-hard. On the positive side, for score-based variational inference, we prove that targets satisfying a log-Sobolev inequality admit polynomial-bond MPO-BM approximations with provable KL guarantees when the loss-induced Hamiltonian is local and has a constant spectral gap. Furthermore, under the same conditions, we construct local importance-sampling estimators and prove that polynomially many local score queries suffice to preserve the KL guarantees.

cs.LG↗

arXiv2026

MemCalib: Benchmarking and Optimizing Memory Use in LLM Agents

The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over its response. Yet this capability has remained largely overlooked. To assess this capability, we introduce MemCalib, a benchmark grounded in realistic memory-system scenarios for evaluating memory use and advancing optimization algorithms. Results on the MemCalib test set reveal that frontier open- and closed-source models struggle to use memory appropriately. They frequently over-use or under-use memory rather than matching each proposition's actual use to its target level, leading to biased, low-quality responses. Experiments with common post-training algorithms, including group relative policy optimization and on-policy self-distillation, further reveal a clear directional skew: trained models improve in one direction while deteriorating in the other. We therefore propose MemCalib-RL, an ordered bidirectional counterfactual credit-assignment algorithm that separates over- and under-use signals and localizes their credit to response tokens through exact atom ablation. Results across model families and scales (Qwen3-8B, Ministral-3-8B-Instruct, and Qwen3.5-35B-A3B) show that MemCalib-RL achieves the best overall performance while better balancing over-use and under-use, with gains generalizing beyond MemCalib in external benchmark evaluation. Further experiments support its design choices and robustness and provide insight into its training dynamics.

cs.LG↗

arXiv2026

Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning

E-commerce videos are information-dense and frequently compared by consumers evaluating products and merchants assessing marketing strategies. However, existing multimodal models mainly focus on single-video understanding and have limited ability to compare information across videos. We introduce AdsCVR, the first e-commerce cross-video reasoning benchmark, containing 2,483 videos and 6,110 question-answer pairs across six reasoning dimensions. Cross- video reasoning requires models to locate fine-grained evidence among many redundant frames and integrate visual details, speech, and on-screen text. We therefore propose AdSeek, an agentic framework that dynamically selects visual and audio tools during multi-turn exploration, replacing static uniform sampling with active evidence acquisition. To address the sparse credit assignment of reinforcement learning, we develop an offline trajectory rectification mechanism that identifies reasoning errors and missing multimodal evidence in RL-generated trajectories. The corrected trajectories provide supervised fine-tuning signals that reduce biases learned during RL. This mechanism supports a rectified bootstrapping pipeline in which initial RL exposes reasoning bottlenecks, supervised fine-tuning corrects them, and a final RL stage further improves the policy. AdSeek achieves 74.30 percent accuracy on the AdsCVR test split, outperforming its Qwen3-VL-8B-Instruct backbone by 27.90 percentage points. It also generalizes to the open- domain CrossVid benchmark, demonstrating effective active evidence gathering.

cs.CV↗

arXiv2026

TRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology

Modern seismic networks resolve earthquake sequences in unprecedented detail, yet explaining how large earthquakes emerge from evolving fault systems remains difficult. We introduce TRACE, a seismology-guided artificial intelligence agent that plans and executes workflows while preserving auditable evidence chains from observations to physical interpretation. We evaluated TRACE through 104 benchmark tasks and two complementary earthquake sequences. For the well-studied 2019 Ridgecrest sequence, TRACE constructed a high-resolution catalog from continuous waveforms and retrospectively recovered delayed cascading activation between the Mw 6.4 and Mw 7.1 earthquakes without a prescribed target interpretation. In the less-understood 2025-2026 Sanriku sequence off northeastern Japan, TRACE developed a testable interpretation of progressive destabilization within a segmented megathrust. Its synthesis linked coupled seismic-aseismic activation around the MJ 6.9 sequence and subsequent persistent, spatially segmented shallow-interface activity to a megathrust patch that lay between regions of past large coseismic slip and later hosted the MJ 7.7 rupture. These results open a path from seismic observations to testable physical insight.

physics.geo-ph↗

arXiv2026

No Task Vector Is an Island: A Comprehensive Study on the Composability of Task Vectors from On-Policy Distillation

Task vectors provide a simple mechanism for composing learned capabilities through model merging. However, the composability of task vectors produced by on-policy distillation (OPD) remains largely unexplored. OPD trains a student using teacher feedback on student-generated trajectories, yielding parameter updates that differ from those produced by the teacher model, usually by reinforcement learning (RL). We therefore ask whether OPD task vectors can complement their RL teacher updates and compose effectively across tasks. Across five domains and two model architectures, we find evidence for both forms of composability. Within a task, merging OPD and RL task vectors can outperform both constituent models, even when the OPD student is weaker than its RL teacher. Across tasks, OPD task-vector compositions achieve higher average scores than corresponding RL compositions in seven of eight backbone-merging-rule comparisons. Parameter-space analyses reveal substantial non-collinearity between OPD and RL updates. Experiment in CODE domain on SMOLLM3-3B shows that the combined direction outperforms either constituent direction at the tested global update norm, supporting directional complementarity in this configuration. Across tasks, OPD updates also show lower overlap among the top-10% feed-forward channels ranked by update energy. Together, these results show that weaker standalone performance does not imply weaker task-vector composability. OPD task vectors can complement stronger RL teacher updates and combine effectively across tasks, highlighting composability as a distinct property for understanding and evaluating post-training updates.

cs.LG↗

arXiv2026

What Does a Stream Model Buy You in Flow Matching?

Stream-level flow matching replaces the linear interpolant of conditional flow matching (CFM) by a Gaussian-process (GP) stream connecting each source--target pair, and reports lower sample error than \icfm{} on 2-Gaussian, MNIST and CIFAR-10 benchmarks. We ask what such a stream model actually contributes. Three results answer the question. (i)~\emph{Reduction.} The stream-level CFM objective depends on the stream law only through the per-time joint law of $(s_t,\sdot_t)$, so the conditional paths a Gaussian stream can reach are exactly the Gaussian conditional paths CFM already parametrises; in the coordinate-wise, shared-scalar-kernel construction gpcfm actually uses, the entire design space collapses to two scalar curves $(m_t,v_t)$, and cross-time covariance affects only estimator variance. (ii)~\emph{The GP is a constrained chart of that space.} One kernel sets both $m_t$ and $v_t$, so the paper's own recipe for widening coverage-shrinking the SE length-scale---destroys the interpolant (the midpoint mean weight falls from $1.03$ to $0.00$). On the 2-Gaussian benchmark this makes the GP chart diverge on $15/200$ runs at high coverage against $0/200$ for a decoupled $(m_t,v_t)$ chart ($p=6.6\times10^{-5}$), and crossing the two curves shows the divergence tracks the mean, not the variance. On MNIST the same sweep does not diverge and the ordering reverses, so whether the coupling is harmful is benchmark-dependent; what holds on both is that the recipe buys nothing---no coverage level beats the paper's own, and past $\max_t\sqrt{v_t}\approx0.6$ both charts degrade. (iii)~\emph{Audit.} The released code does not implement the mechanism it describes: state and velocity are drawn independently ($\mathrm{corr}=0.00\pm0.01$ against an intended $\pm0.83$--$0.99$).

cs.LG↗

arXiv2026

Neural Bridge Processes

Learning stochastic functions from partially observed context-target pairs requires models that are expressive, uncertainty-aware, and strongly conditioned on inputs. Neural Diffusion Processes (NDPs) improve expressivity with denoising diffusion, but their forward process is input-independent; inputs only enter the reverse denoiser, so the noisy training states themselves do not encode the conditioning inputs. We propose Neural Bridge Processes (NBPs), which replace the unconditional forward kernel with an input-anchored bridge trajectory. When input and output dimensions differ, NBP learns an output-space anchor $a_ψ(x)=P_ψ(x)$, allowing coordinates or other inputs to guide the generative path without changing the denoising backbone. We show theoretically that process-level anchoring induces pathwise input distinguishability, injects information about x into noisy states, and creates a direct gradient pathway unavailable to NDPs. Experiments on synthetic regression, EEG, CylinderFlow, and image regression show consistent improvements. Additional ablations show that the gains come from the full bridge construction with learned alignment, and that the same input-anchored path principle transfers to Flow Matching Neural Processes. These results suggest that bridge-anchored generative paths provide a general mechanism for strengthening conditional stochastic function modeling.

cs.LG↗