arXiv subjects

Cong Ma

Publications and source records attributed to Cong Ma.

At least 19 recordsLinked to original sources

arXiv2026

Finding Is Not Returning, Returning Is Not Reconstructing: A Multi-Dimensional Evaluation of Agent Social Re-entry

As Large Language Model (LLM) agents increasingly participate in persistent social environments, understanding their long-term social interaction capabilities becomes increasingly important. While existing research has advanced long-term memory and conversational context retrieval, less attention has been paid to whether agents can autonomously re-engage with previously inactive conversations. In particular, remembering a past interaction does not necessarily mean that an agent can identify when to revisit it, decide to return, or reconstruct the context needed for a coherent continuation. To investigate this gap, we introduce agent social re-entry as a multi- dimensional evaluation problem, distinguishing three complementary capabilities: Finding, Returning, and Reconstructing. We develop a shared-snapshot evaluation framework that measures these dimensions independently, allowing us to examine how conversational resurfacing and persistent memory relate to different aspects of social re-entry. Evaluations across six LLM configurations show that resurfacing substantially improves target conversation identification, while persistent memory is associated with higher rates of autonomous target-directed replying. However, neither improvement is accompanied by consistent gains in contextual reconstruction. These results highlight the distinction between accessing previous conversations, choosing to re-engage, and maintaining conversational continuity. Our framework provides a way to evaluate these capabilities separately rather than relying on memory retrieval or conversational response quality alone.

cs.AI↗

arXiv2026

Dimension-free comparison inequalities between $f$-divergences for Gaussian location mixtures

We establish dimension-free comparison inequalities between the Kullback-Leibler (KL) and $χ^2$-divergences and the squared Hellinger distance for Gaussian location mixtures with compactly supported mixing distributions. We show that both divergences are bounded by the squared Hellinger distance up to constants depending only on the radius of the support, independently of the ambient dimension and the number of mixture components. These results resolve an open question raised by \cite{jia2023entropic} and strengthen existing comparison inequalities. Our proof relies on a Gaussian interpolation argument that relates the derivatives of these divergences to differences between posterior means.

math.ST↗

arXiv2026

The Statistical Benefits of Multiple Responses for Learning from Demonstrations

Many generative systems return multiple candidate responses and are evaluated according to the best one. Recent work shows that, when demonstrations are optimal, pass@$k$ can reduce the sample complexity of learning from demonstrations by a logarithmic factor in $k$. We ask what happens when the demonstrator is not assumed to be optimal. We find that multiple responses provide a qualitatively stronger benefit in this setting. In a finite reward-class model with no reward feedback, moving from pass@$1$ to any pass@$k$ with $k\ge2$ changes the worst-case dependence on target accuracy from $1/\varepsilon^2$ to $1/\varepsilon$, uniformly over demonstrator quality. Under standard evaluation, where an unknown reward is fixed before training, increasing $k$ provides an additional and distinct benefit: the optimal dependence on a reward class of size $N$ improves from $\log N$ to $\log N/\log k$. We further show that these two effects can be separated. Under robust evaluation, where one learned policy must compete with the demonstrator simultaneously for every reward in the class, the fast $1/\varepsilon$ dependence persists, while the $1/\log k$ improvement can disappear. We establish matching upper and lower bounds in the corresponding regimes and give a greedy multiplicative-weights learner achieving the upper bounds without any assumption on demonstrator quality.

stat.ML↗

arXiv2026

Graph-monotone entrywise guarantees for MLE and Rank Centrality on general comparison graphs

Pairwise comparisons are widely used to infer latent scores and identify top-ranked items. Although sharp statistical guarantees are available under uniform sampling, real data often induce irregular comparison graphs with heterogeneous observation counts across pairs. In this paper, we study an arbitrary fixed comparison graph under the Bradley--Terry--Luce model with minimal assumptions. We prove that both the standard maximum likelihood estimator and Rank Centrality achieve a high-probability entrywise error rate of order $1/\sqrt{λ_{\mathcal{D}}}$ up to logarithmic and dynamic-range factors, where $λ_{\mathcal{D}}$ is the algebraic connectivity of the count-weighted observation graph. This guarantee is graph-monotone since $λ_{\mathcal{D}}$ cannot decrease when additional comparisons are added. Under heterogeneous sampling, where comparison pairs are sampled independently with unequal probabilities, our guarantee improves existing error bounds or requires weaker assumptions. We further extend our analysis to show that both estimators are robust against outcome-adaptive augmentation, where an adversary can choose additional comparison pairs after observing the initial outcomes.

math.ST↗

arXiv2026

Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding

Self-supervised pre-training with Vision Transformers, including Masked Autoencoders (MAE), is difficult to apply to gigapixel scientific images. Random masking is poorly matched to the structured, multi-scale morphology of scientific data, while uniform tokenization produces prohibitively long sequences that make $O(N^2)$ attention impractical. We propose SGMA, a structure-guided masked autoencoding framework for ultra-high-resolution scientific images. SGMA couples two components: a content-adaptive quadtree tokenizer that compresses gigapixel images into a fixed-length sequence, and a structure-conditioned masking process that biases reconstruction toward spatially informative regions. To stabilize this process across scales, we introduce Damped Accumulation (DA), which aggregates signal-dependent responses across the tree into a structure canvas used to guide masking. The resulting pre-training task preserves fine microstructure while remaining compatible with standard ViT encoders and MAE-style reconstruction. Across electron microscopy, whole-slide optical microscopy, and X-ray CT datasets, SGMA consistently outperforms MAE baselines. It achieves 95.68% Dice on the 8K x 8K x 28K SpringXCT dataset, improving over the same-architecture MAE baseline by +13.00 points, and 83.21% Dice on the 32K^2 WSI PAIP dataset, improving by +16.84 points, while providing up to a 24.8x inference speedup.

cs.CV↗

arXiv2026

Thor: Towards Human-Inspired Whole-Body Reactions for Intense Contact-Rich Environments

Maintaining whole-body stability and motion tracking under large interaction forces remains challenging for humanoids. We present Thor, a reinforcement learning framework for forceful humanoid loco-manipulation. Thor jointly trains lower-body, waist, and upper-body policies with shared whole-body observations and body-specific rewards to coordinate locomotion and force adaptation, waist posture regulation, and upper-body motion tracking. We further introduce a force-adaptive torso-tilt (FAT2) objective that derives a load-dependent horizontal center-of-mass offset reference from quasi-static moment balance. Capacity-matched simulation blations show that the three-policy architecture improves tracking under large external force disturbances, while real-world ablations demonstrate that FAT2 increases peak pulling capability. On the Unitree G1, Thor achieves mean peak dual-hand pulling forces of 167.7 N and 145.5 N during backward and forward locomotion, exceeding the best-performing baseline by 68.9% and 74.7%, respectively. Real-world demonstrations include opening a fire door with one hand using approximately 60 N of pulling force and towing a 1.7-ton passenger car.

cs.RO↗

arXiv2026

An Efficient Out-of-Core Tomographic Imaging Framework for Edge Devices

Computed Tomography (CT) is an essential 3D imaging technology widely used in medical diagnostics and scientific research. However, performing CT imaging on edge devices is challenging due to limitations in computational power, memory capacity, and energy budget. This paper presents an efficient CT reconstruction framework, called edgeFBP, designed for Nvidia Jetson System-on-Chip (SoC) devices. edgeFBP adopts an end-to-end pipeline design for efficient out-of-core image reconstruction under tight power and memory constraints. edgeFBP utilizes a mixed-precision strategy leveraging half-precision Tensor Cores (TCs) to accelerate the bottleneck back-projection (BP) kernel. edgeFBP achieves a 1.83x speedup over the widely used RTK library on Jetson Nano and a 2.56x speedup on Jetson AGX. Under a strict 25-Watt power budget, edgeFBP on Jetson Nano achieves up to 5-48x higher energy efficiency than an Nvidia DGX A100, enabling datacenter-scale imaging on constrained edge devices.

cs.DC↗

arXiv2026

Bias-Corrected Subspace Intersection: Minimax-Optimal Shared Subspace Estimation in Multi-View Data

Estimating a low-dimensional subspace shared across noisy data matrices is a fundamental problem in multi-view matrix estimation. We study this problem under the two-view JIVE model, where each data matrix contains shared and view-specific low-rank components. We demonstrate that standard plug-in subspace intersection, including AJIVE, suffers from a second-order bias caused by direction-dependent leakage of the empirical singular vectors. We propose bias-corrected subspace intersection (BCSI), which removes this bias before estimating the shared subspace. We establish finite-sample risk bounds for BCSI that accommodate unequal view dimensions, signal strengths, and view-specific ranks and require no condition-number assumptions on the signal matrices. When the shared and view-specific ranks are comparable, these bounds match our minimax lower bounds up to universal constants. The resulting minimax rate contains a new second-order term, arising from quadratic leakage perturbations relative to the shrinking spectral gap when the view-specific subspaces are nearly aligned. This term is absent from previous JIVE minimax lower bounds. Numerical experiments demonstrate the advantage of BCSI over AJIVE when the leakage bias is pronounced. Along the way, we establish a nonasymptotic concentration result for the bias-corrected leakage Gram matrix of a rectangular spiked matrix, which may be of independent interest.

stat.ME↗

arXiv2026

LISM: Long-range Integrative State space Models via Input-Latent State Interactions

State space models (SSMs) are an emerging paradigm that achieves linear-time scaling, however, they intrinsically suffer from "curse of memory". The memory of SSMs, including Mamba, decays exponentially as long as the recursive update is stable. In this work, we developed Long-range Integrative State space Models (LISM) to mitigate the curse of memory in SSMs. LISM allows the recursive update to occasionally be unstable, which enables longer memory retention, and incorporates a dynamic input-state interaction mechanism to identify inputs that should be memorized for longer periods. We theoretically establish probability bounds for the overall stability of LISM and derive a probabilistic stability condition to guide parameterization and training. We evaluated LISM's performance on multiple tasks, a synthetic Selective Copy task, two real language tasks WikiText-103 and LRA Retrieval, and an additional biological prediction task. LISM achieved the best performance on the Selective Copying task, WikiText-103, and the biological prediction task compared to SSM-based models and achieved comparable performance on the LRA-Retrieval task with the state-of-the-art. Beyond average performance, LISM also shows strong repeatability across runs. In the two real language tasks, LISM reduced the relative performance variance (coefficient of variation) by an average of 33.3%, achieving a standard deviation of $\pm$0.30% on WikiText-103 compared to $\pm$0.46% for Mamba-2. The implementation of LISM is available at https://github.com/CM-Compbio-Group/LISM_dev.

cs.LG↗

arXiv2026

Sample-efficient inductive matrix completion with noise and inexact side-information

Inductive matrix completion (IMC) is a variant of low-rank matrix completion that incorporates row and column side-information. In principle, it can reduce the effective dimension of the recovery problem from the ambient matrix size to the dimension of the side-information features. Existing theory, however, does not fully realize this advantage in the noisy setting: sample-efficient guarantees only apply to noiseless recovery, while noisy guarantees require sample sizes comparable to ordinary matrix completion. This paper closes this gap for noisy IMC. We analyze a nonconvex projected gradient descent algorithm with spectral initialization and prove that, under exact side-information, it achieves linear convergence and stable recovery at a sample complexity governed by the effective side-information dimension rather than the ambient matrix dimension. The key technical ingredient is a local regularity condition for the IMC loss that holds at this reduced sample size, despite the mismatch between the observation pattern and the side-information subspaces. We further extend the analysis to inexact side-information, showing that the same reduced sample complexity is preserved and that the estimation error degrades optimally with the level of subspace misspecification. Motivated by this trade-off, we also propose a penalized interpolation between IMC and ordinary matrix completion that balances sample efficiency against robustness to imperfect side-information. Simulations and experiments on the MovieLens dataset support the theoretical findings and illustrate the practical benefits of exploiting side-information in low-sample regimes.

stat.ML↗

arXiv2026

EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance

Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning, often leading to inefficient exploration and sparse rewards. To mitigate this issue, we propose Expert-Assisted Policy Optimization (EAPO), a novel RL framework that enhances exploration by incorporating multi-turn interactions with external experts during training. Unlike prior methods, where policies reason in isolation, EAPO incentivizes the policy to adaptively determine when and how to consult experts, yielding richer reward signals and more reliable reasoning trajectories. External assistance ultimately internalizes expert knowledge into the policy model, amplifying the model's inherent reasoning capabilities. During evaluation, the policy model has been well-optimized to solve questions independently, producing improved reasoning paths and more accurate solutions. On AIME 2024/2025 and AIMO 2025, EAPO consistently outperforms expert-assisted, expert-distilled, and RL baselines, averaging a 5-point gain over self-exploration RL, and also generalizes to non-math benchmarks, including HumanEval, HLE, GPQA, MMLU, EvalPlus, HotpotQA, and SimpleQA.

cs.AI↗

arXiv2026

When Are Trade-Off Functions Testable from Finite Samples?

We study finite-sample inference for the trade-off function of two unknown probability distributions, the function that traces the optimal type I/type II error frontier in binary testing. Given samples from distributions $P$ and $Q$, we consider the problem of testing whether their trade-off function lies above a benchmark curve $f_0$ or falls below a weaker benchmark $f_1$. Without structural restrictions, this problem is impossible uniformly over nonparametric classes. We identify a sharp condition under which it becomes possible. The key structural assumption is that the Neyman--Pearson rejection regions for $(P,Q)$ are attainable, up to null sets, by a prescribed class $S$ of measurable sets. Within this exact attainability framework, finite Vapnik--Chervonenkis dimension of $S$ is both sufficient and necessary for nontrivial finite-sample testing. We construct a test with nonasymptotic error guarantees: type I error control is valid without assuming attainability, while power holds uniformly over attainable alternatives satisfying an explicit separation condition. By inverting the test, we also obtain simultaneous confidence bands for the whole trade-off curve. Finally, we study the sharpness and robustness of the procedure. In the monotone likelihood-ratio model, we derive local separation rates and prove matching lower bounds up to logarithmic factors. We also allow approximate, rather than exact, attainability; this extension yields finite-sample guarantees for univariate log-concave distributions by approximating their rejection regions with unions of intervals.

math.ST↗

arXiv2026

SoK: Security of Autonomous LLM Agents in Agentic Commerce

Autonomous large language model (LLM) agents such as OpenClaw are pushing agentic commerce from human-supervised assistance toward machine actors that can negotiate, purchase services, manage digital assets, and execute transactions across on-chain and off-chain environments. Protocols such as the Trustless Agents standard (ERC-8004), Agent Payments Protocol (AP2), OKX Agent Payments Protocol (APP), the HTTP 402-based payment protocol (x402), Agent Commerce Protocol (ACP), the Agentic Commerce standard (ERC-8183), and Machine Payments Protocol (MPP) enable this transition, but they also create an attack surface that existing security frameworks do not capture well. This Systematization of Knowledge (SoK) develops a unified security framework for autonomous LLM agents in commerce and finance. We organize threats along five dimensions: agent integrity, transaction authorization, inter-agent trust, market manipulation, and regulatory compliance. From a systematically curated public corpus of academic papers, protocol documents, industry reports, and incident evidence, we derive 12 cross-layer attack vectors and show how failures propagate from reasoning and tooling layers into custody, settlement, market harm, and compliance exposure. We then propose a layered defense architecture addressing authorization gaps left by current agent-payment protocols. Overall, our analysis shows that securing agentic commerce is inherently a cross-layer problem that requires coordinated controls across LLM safety, protocol design, identity, market structure, and regulation. We conclude with a research roadmap and a benchmark agenda for secure autonomous commerce.

cs.CR↗

arXiv2026

Trans-Glasso: A Transfer Learning Approach to Precision Matrix Estimation

Precision matrix estimation is essential in various fields; yet it is challenging when samples for the target study are limited. Transfer learning can enhance estimation accuracy by leveraging data from related source studies. We propose Trans-Glasso, a two-step transfer learning method for precision matrix estimation. First, we obtain initial estimators using a multi-task learning objective that captures shared and unique features across studies. Then, we refine these estimators through differential network estimation to adjust for structural differences between the target and source precision matrices. Under the assumption that most entries of the target precision matrix are shared with source matrices, we derive non-asymptotic error bounds and show that Trans-Glasso achieves minimax optimality under certain conditions. Extensive simulations demonstrate Trans Glasso's superior performance compared to baseline methods, particularly in small-sample settings. We further validate Trans-Glasso in applications to gene networks across brain tissues and protein networks for various cancer subtypes, showcasing its effectiveness in biological contexts. Additionally, we derive the minimax optimal rate for differential network estimation, representing the first such guarantee in this area. The Python implementation of Trans-Glasso, along with code to reproduce all experiments in this paper, is publicly available at https://github.com/boxinz17/transglasso-experiments.

stat.ML↗

arXiv2026

Learning to Answer from Correct Demonstrations

We study the problem of learning to generate an answer (or completion) to a question (or prompt), where there could be multiple correct answers, any one of which is acceptable at test time. Learning is based on demonstrations of some correct answer to each training question, as in Supervised Fine Tuning (SFT). We formalize the problem as imitation learning (i.e., apprenticeship learning) in contextual bandits, with offline demonstrations from some expert (optimal, or very good) policy, without explicitly observed rewards. In contrast to prior work, which assumes the demonstrator belongs to a bounded-complexity policy class, we propose relying only on the underlying reward model (i.e., specifying which answers are correct) being in a bounded-complexity class, which we argue is a strictly weaker assumption. We show that likelihood-maximization methods can fail in this setting, and instead present an approach that learns to answer nearly as well as the demonstrator, with sample complexity logarithmic in the cardinality of the reward class. Our method is similar to Syed and Schapire 2007, when adapted to a contextual bandit (i.e., single step) setup, but is a simple one-pass online approach that enjoys an "optimistic rate" (i.e., $1/\varepsilon$ when the demonstrator is optimal, versus $1/\varepsilon^2$ in Syed and Schapire), and works even with arbitrarily adaptive demonstrations.

cs.LG↗

arXiv2026

ShoppingComp: Are LLMs Really Ready for Your Shopping Cart?

We present ShoppingComp, a challenging real-world benchmark for comprehensively evaluating LLM-powered shopping agents on three core capabilities: precise product retrieval, expert-level report generation, and safety critical decision making. Unlike prior e-commerce benchmarks, ShoppingComp introduces difficult product discovery queries with many constraints, while guaranteeing open-world products and enabling easy verification of agent outputs. The benchmark comprises 145 instances and 558 scenarios, curated by 35 experts to reflect authentic shopping needs. Results reveal stark limitations of current LLMs: even state-of-the-art models achieve low performance (e.g., 17.76\% for GPT-5.2, 15.82\% for Gemini-3-Pro).Error analysis reflects limitations in core agent competencies, including information grounding in open-world environments, reliable verification of multi-constraint requirements, consistent reasoning over noisy and conflicting evidence, and risk-aware decision making. By exposing these capability gaps, ShoppingComp characterizes the trust threshold that AI systems must cross before they can be proactively trusted for reliable real-world decision making. Our code and dataset are available at https://github.com/ByteDance-BandAI/ShoppingComp.

cs.CL↗

arXiv2025

The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing

We propose $\textsf{ScaledGD($λ$)}$, a preconditioned gradient descent method to tackle the low-rank matrix sensing problem when the true rank is unknown, and when the matrix is possibly ill-conditioned. Using overparametrized factor representations, $\textsf{ScaledGD($λ$)}$ starts from a small random initialization, and proceeds by gradient descent with a specific form of damped preconditioning to combat bad curvatures induced by overparameterization and ill-conditioning. At the expense of light computational overhead incurred by preconditioners, $\textsf{ScaledGD($λ$)}$ is remarkably robust to ill-conditioning compared to vanilla gradient descent ($\textsf{GD}$) even with overprameterization. Specifically, we show that, under the Gaussian design, $\textsf{ScaledGD($λ$)}$ converges to the true low-rank matrix at a constant linear rate after a small number of iterations that scales only logarithmically with respect to the condition number and the problem dimension. This significantly improves over the convergence rate of vanilla $\textsf{GD}$ which suffers from a polynomial dependency on the condition number. Our work provides evidence on the power of preconditioning in accelerating the convergence without hurting generalization in overparameterized learning.

cs.LG↗

arXiv2025

IndiSeek learns information-guided disentangled representations

Learning disentangled representations is a fundamental task in multi-modal learning. In modern applications such as single-cell multi-omics, both shared and modality-specific features are critical for characterizing cell states and supporting downstream analyses. Ideally, modality-specific features should be independent of shared ones while also capturing all complementary information within each modality. This tradeoff is naturally expressed through information-theoretic criteria, but mutual-information-based objectives are difficult to estimate reliably, and their variational surrogates often underperform in practice. In this paper, we introduce IndiSeek, a novel disentangled representation learning approach that addresses this challenge by combining an independence-enforcing objective with a computationally efficient reconstruction loss that bounds conditional mutual information. This formulation explicitly balances independence and completeness, enabling principled extraction of modality-specific features. We demonstrate the effectiveness of IndiSeek on synthetic simulations, a CITE-seq dataset and multiple real-world multi-modal benchmarks.

stat.ML↗