arXiv subjects

Weitong Zhang

Publications and source records attributed to Weitong Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Predicting Quantization Price for Selecting PTQ Configurations Before Deployment

Weight-space post-training quantization (PTQ) must choose finite formats, granularities, quantizer families, transformations, and bits before the completed quantized model reveals its output-distribution drift. Existing PTQ methods predict important pieces of this degradation, including reconstruction error, Hessian sensitivity, transformation effects, and downstream loss, but these pieces are usually scored after fixing the quantization geometry or inside separate configuration families. We formulate weight-space PTQ as pre-deployment configuration selection using priced layer-output error. Each admissible layer configuration is treated as an error generator with a deployment cost, which induces a layer-output error covariance $\boldsymbolΣ_l(α_l)$, and the full-precision model prices that covariance by downstream curvature, $\widehatρ_l(α_l)=\frac{1}{2}\operatorname{Tr}\left(\widehat{\mathbf{H}}_l\,\widehat{\boldsymbolΣ}_l(α_l)\right)$. The price follows from full-precision-to-quantized forward KL, whose first-order term cancels at the reference model. It turns reconstruction and diagonal scores into reduced proxies that drop price factors, while finite formats, codebooks, granularities, and equivalent transformations become comparable candidates through the covariances they induce and the costs they pay. A trace reduction then yields a calibration-time price table and a budgeted price-guided selector, making fixed-geometry bit allocation a special case rather than the organizing problem.

cs.CL↗

arXiv2026

A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models

We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data coverage and severe performance degradation. We propose a solution that leverages robot simulators to achieve online imitation learning. Our sim-to-real framework is based on world models and combines online imitation pretraining with offline finetuning. By leveraging online interactions, our approach alleviates the data coverage limitations of offline methods, leading to improved robustness and reduced performance degradation during finetuning. It also enhances generalization during domain transfer. Our empirical results demonstrate its effectiveness, improving success rates by at least 31.7% in sim-to-sim transfer and 23.3% in sim-to-real transfer over existing offline imitation learning baselines.

cs.RO↗

arXiv2026

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

We study length inflation in on-policy distillation (OPD), where student responses can become excessively long and even exhaust the generation budget. We identify \emph{termination-token mismatch} between base students and post-trained teachers as an important source of this behavior. Across Qwen3, Llama, and Gemma, the two models can place their stopping probability on different EOS tokens, even when their declared stopping sets are identical. This mismatch can suppress the student's preferred termination action without reliably transferring the teacher-preferred alternative. We show that aligning the decoding stopping set alone is insufficient, while treating functionally equivalent EOS tokens as a shared semantic stopping action substantially mitigates mismatch-induced length inflation across all three model families. To further understand how termination behavior evolves over training, we study OPD across different K2-Horizon training stages. This stage-wise analysis shows that termination preferences can shift substantially during training, while also revealing a distinct length inflation late in the OPD run that persists beyond termination alignment. Together, these results identify termination mismatch as an important, but not exhaustive, source of OPD length dynamics. We release an implementation incorporating the proposed termination-handling corrections.

cs.LG↗

arXiv2026

CPAgents: Agentic Composite Phenotype Generation for Cardiac Disease Association

Identifying robust associations between cardiac imaging phenotypes and clinical diseases is fundamental to population-scale cardiovascular research and reliable risk stratification. However, current phenome-wide association studies rely on pre-defined, single-variable phenotypes or expert-crafted features, which limits their ability to capture clinically meaningful non-linear effects and cross-phenotype interactions. To address this, we propose CPAgents, an iterative phenotype-Composition framework for cardiovascular Phenome-wide association study (PheWAS) that automatically constructs and validates interpretable composite phenotypes (e.g., polynomial, ratio, and interaction forms) from base imaging features. Specifically, our system coordinates three agents: (i) an Analyst that identifies statistical pathologies and nominates candidate transformations; (ii) a Proposer that generates constrained, medically and statistically motivated expressions under numerical safety rules; and (iii) a Verifier that evaluates candidates using multi-stage criteria and produces transparent evidence trails for accepted phenotypes. Evaluated on a population-scale cardiac imaging cohort, the discovered composite phenotypes markedly improve disease discrimination: across 72 classifier-disease-metric combinations, our variants achieve the top rank in 56 cases versus 18 for baselines, with gains observed across all nine clinical disease categories. Our framework yields compact, clinically interpretable phenotype formulas with transparent evidence trails, enabling scalable discovery of stronger phenotype-disease associations beyond expert-driven feature selection.

cs.LG↗

arXiv2026

Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering

Small vision-language models (2-8B) are well-suited for clinical deployment due to privacy constraints, limited connectivity, and low-latency requirements favouring on-device or on-premise inference. However, their limited capacity exacerbates the generation of plausible but incorrect outputs. We extend game-theoretic decoding, previously restricted to text-only, closed-ended NLP tasks, to vision-language models for open-ended Medical VQA. We introduce a semantically aware Wasserstein stopping criterion that replaces lexical order matching, enabling convergence based on semantic consensus among near-synonymous candidate answers and avoiding unnecessary iterations caused by clinically equivalent ranking swaps. On VQA-RAD and PathVQA, we obtain consistent, statistically significant improvements over greedy and discriminative baselines. On VQA-RAD, we improve Qwen3-VL-2B by +3.5 percentage points (p < 0.01), surpassing the greedy 4B model, with similar trends at larger scales. On PathVQA, Gemma-3-4B with BDG matches MedGemma-4B under greedy decoding despite no domain-specific fine-tuning. At accuracy parity with classic BDG, the Wasserstein criterion reduces average convergence iterations by approximately 20%, improving inference efficiency while preserving the game-theoretic equilibrium behaviour. Code is available at https://github.com/luca-hagen/ Wasserstein-BDG-medical-VQA.

cs.CV↗

arXiv2026

Your Self-Play Algorithm is Secretly an Adversarial Imitator: Understanding LLM Self-Play through the Lens of Imitation Learning

Self-play post-training methods has emerged as an effective approach for finetuning large language models and turn the weak language model into strong language model without preference data. However, the theoretical foundations for self-play finetuning remain underexplored. In this work, we tackle this by connecting self-play finetuning with adversarial imitation learning by formulating finetuning procedure as a min-max game between the model and a regularized implicit reward player parameterized by the model itself. This perspective unifies self-play imitation and general preference alignment within a common framework. Under this formulation, we present a game-theoretic analysis showing that the self-play finetuning will converge to it's equilibrium. Guided by this theoretical formulation, we propose a new self-play imitation finetuning algorithm based on the $χ^2$-divergence variational objective with bounded rewards and improved stability. Experiments on various of language model finetuning tasks demonstrate consistent improvements over existing self-play methods and validate our theoretical insights.

cs.LG↗

arXiv2026

OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning

We study on-policy self-distillation (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories. Despite its promise, OPSD can suffer from training instability due to a pattern mismatch between teacher and student responses. Self-reflected teacher responses may introduce reflection-induced biases and response templates that miscalibrate token-level supervision, ultimately harming the student's reasoning ability. To mitigate this issue, we propose OGLS-SD, an outcome-guided logit-steering framework that leverages verifiable outcome rewards to calibrate privileged teacher logits. Specifically, OGLS-SD contrasts teacher logits induced by successful and failed on-policy trajectories, constructing an outcome-discriminative steering direction for token-level guidance. Experiments on mathematical reasoning benchmarks show that OGLS-SD stabilizes self-distillation and improves performance over standard OPSD and other variants.

cs.LG↗

arXiv2026

LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning Distillation

We study trajectory selection for reasoning distillation, where teacher-generated reasoning trajectories are selectively used as supervision for a student model. Existing methods rely on heuristics such as trajectory quality or model confidence, but they often overlook whether a trajectory is learnable by the student. In this paper, we present LARK, a learnability-grounded method for reasoning trajectory selection. LARK selects trajectories that the student can learn efficiently while preserving the generalization of the full training distribution. At the core of LARK is a learnability factor $ρ$, which characterizes the rate at which the student's training loss decreases. To estimate this rate efficiently and maintain generalization, we introduce a learnability proxy and a $χ^2$-regularized selection policy that balances learnability and distributional coverage, both with strong theoretical guarantees on their estimation error. Empirically, LARK consistently outperforms data selection baselines across multiple base models and reasoning tasks. Diagnostic analyses show that the LARK score predicts downstream training utility and that LARK-selected trajectories induce faster supervised fine-tuning loss reduction. Our code is available at https://github.com/Tianrun-Yu/LARK.

cs.LG↗

arXiv2026

Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning

Conditioned Sequence Models (CSMs) learn policies by treating return-to-go (RTG) as a control signal. However, existing CSMs often treat the RTGs as simple numerical inputs rather than aligning them with the performance of their policies. In this paper, we propose Q-ALIGN DT, a framework that enforces this alignment by ensuring the $Q$-value of the output policy is consistent with the input RTG. By leveraging a $Q$ function to provide dense guidance to CSMs and further fine-tuning it using an RTG-perturbation technique with the CSM, our method ensures that higher RTGs are consistently mapped to trajectories with higher expected returns. Theoretically, we show that Q-ALIGN DT can efficiently learn the desired policy and output a near-optimal one when the RTG is sufficiently high. Empirically, we demonstrate through extensive experiments that Q-ALIGN DT achieves superior controllability and performance across the D4RL benchmark. Remarkably, our model effectively learns a structured family of policies that maintains precise alignment and generalizes to tasks like velocity-tracking where prior methods fail.

cs.LG↗

arXiv2026

Moment Matching Q-Learning

Score-based and flow-based generative models exhibit remarkable expressive capacity in capturing complex distributions, and have been extensively deployed in tasks ranging from image generation to reinforcement learning. Nevertheless, these models suffer from prolonged inference latency, which imposes a significant computational bottleneck in RL with iterative sampling. To overcome this limitation, we propose a new framework named Moment Matching Q-Learning (MoMa QL), which utilizes a technique from statistical hypothesis testing known as maximum mean discrepancy (MMD) that intend to match all orders of statistics between the original and target distribution. By enforcing strong regularization on all moment statistics, this algorithm guarantees distribution-level convergence for conditional score function and remains stable under various hyperparameters. Empirically, we show that our method MoMa QL is more computationally efficient with a comparable if not competitive performance in various D4RL tasks. Remarkably, by accelerating the action sampling process for flow-based policies, MoMa QL demonstrates superior performance in offline-to-online RL tasks because of faster and stronger adaptability for online interactive finetuning.

cs.LG↗

arXiv2026

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail and inform the next attempt, and lessons accumulate across cycles. Existing autonomous research systems often model this process as a linear pipeline: they rely on single-agent reasoning, stop when execution fails, and do not carry experience across runs. We present AutoResearchClaw, a multi-agent autonomous research pipeline built on five mechanisms: structured multi-agent debate for hypothesis generation and result analysis, a self-healing executor with a \textsc{Pivot}/\textsc{Refine} decision loop that transforms failures into information, verifiable result reporting that prevents fabricated numbers and hallucinated citations, human-in-the-loop collaboration with seven intervention modes spanning full autonomy to step-by-step oversight, and cross-run evolution that converts past mistakes into future safeguards. On ARC-Bench, a 25-topic experiment-stage benchmark, AutoResearchClaw outperforms AI Scientist v2 by 54.7%. A human-in-the-loop ablation across seven intervention modes reveals that precise, targeted collaboration at high-leverage decision points consistently outperforms both full autonomy and exhaustive step-by-step oversight. We position AutoResearchClaw as a research amplifier that augments rather than replaces human scientific judgment. Code is available at https://github.com/aiming-lab/AutoResearchClaw.

cs.AI↗

arXiv2026

GeomHerd: A Forward-looking Herding Quantification via Ricci Flow Geometry on Agent Interactive Simulations

Herding -- where agents align their behaviors and act collectively -- is a central driver of market fragility and systemic risk. Existing approaches to quantify herding rely on price-correlation statistics, which inherently lag because they only detect coordination after it has already moved realised returns. We propose GeomHerd, a forward-looking geometric framework that bypasses this observability lag by quantifying coordination directly on upstream agent-interaction graphs. To generate these graphs, we treat a heterogeneous LLM-driven multi-agent simulator -- each financial trader instantiated by a persona-conditioned LLM call -- as a forecastable world, and evaluate the geometric pipeline on the Cividino--Sornette continuous-spin agent-based substrate as our headline financial testbed. By tracking the discrete Ollivier--Ricci curvature of these action graphs, GeomHerd captures the structural topology of emerging coordination. Theoretically, we establish a mean-field bridge mapping our graph-theoretic metric to CSAD, the classical macroscopic herding statistic, linking GeomHerd to downstream price-dispersion measurement. Empirically, GeomHerd anticipates herding long before aggregate market baselines: on the continuous-spin substrate, our primary detector fires a median of 272 steps before order-parameter onset; a contagion detector ($β_{-}$) recalls 65% of critical trajectories 318 steps early; and on co-firing trajectories the agent-graph signal precedes price-correlation-graph baselines by 40 steps. As a complementary indicator, the effective vocabulary of agent actions contracts during cascades. The geometric signature transfers out-of-domain to the Vicsek self-driven-particle model, and a curvature-conditioned forecasting head reduces cascade-window log-return MAE over detector-conditioned and price-only baselines.

cs.MA↗

arXiv2026

Provably Efficient Offline-to-Online Value Adaptation with General Function Approximation

We study value adaptation in offline-to-online reinforcement learning under general function approximation. Starting from an imperfect offline pretrained $Q$-function, the learner aims to adapt it to the target environment using only a limited amount of online interaction. We first characterize the difficulty of this setting by establishing a minimax lower bound, showing that even when the pretrained $Q$-function is close to optimal $Q^\star$, online adaptation can be no more efficient than pure online RL on certain hard instances. On the positive side, under a novel structural condition on the offline-pretrained value functions, we propose O2O-LSVI, an adaptation algorithm with problem-dependent sample complexity that provably improves over pure online RL. Finally, we complement our theory with neural-network experiments that demonstrate the practical effectiveness of the proposed method.

cs.LG↗

arXiv2026

A Dynamic Equilibrium Model for Automated Market Makers

Automated Market Makers (AMMs) are a central component of decentralized exchanges, yet their equilibrium foundations and microeconomic mechanisms remain incompletely understood. This paper develops a dynamic equilibrium framework for Constant Function Market Makers (CFMMs) that formalizes the strategic interaction between arbitrageurs and liquidity providers (LPs) over time. We make three main contributions. First, we derive and empirically validate an intrinsic buy-sell asymmetry in CFMM price impact. Even in the absence of directional price movements, the geometric structure of constant product AMMs implies systematically different execution costs for buying and selling, a prediction that we confirm using on-chain transaction data. Second, we characterize the optimization problems of arbitrageurs and LPs in closed form, incorporating slippage and fees. In a baseline environment with only informed arbitrageurs, we show that providing liquidity is strictly dominated for LPs: arbitrage-driven price corrections generate negative jump returns that cannot be offset by fees, yielding a degenerate equilibrium with minimal liquidity provision. Third, motivated by empirical evidence, we extend the model to include agent heterogeneity, endogenous gas fees, and time varying volatility. In this extended environment, noise trading, arbitrage races, and execution costs jointly determine LP returns, giving rise to an interior equilibrium in which optimal liquidity provision is non-monotonic in volatility and exhibits a hump-shaped relationship. Overall, this paper builds a dynamic equilibrium model calibrated on extensive data that characterize the complex interaction between informed arbitrageurs, noise traders, and liquidity providers.

econ.GN↗

arXiv2026

Provable and Practical In-Context Policy Optimization for Self-Improvement

We study test-time scaling, where a model improves its answer through multi-round self-reflection at inference. We introduce In-Context Policy Optimization (ICPO), in which an agent optimizes its response in context using self-assessed or externally observed rewards without modifying its parameters. To explain this ICPO process, we theoretically show that with sufficient pretraining under a novel Fisher-weighted logit-matching objective, a single-layer linear self-attention model can provably imitate policy-optimization algorithm for linear bandits. Building on this theory, we propose Minimum-Entropy ICPO (ME-ICPO), a practical algorithm that iteratively uses its response and self-assessed reward to refine its response in-context at inference time. By selecting the responses and their rewards with minimum entropy, ME-ICPO ensures the robustness of the self-assessed rewards via majority voting. Across standard mathematical reasoning tasks, ME-ICPO attains competitive, top-tier performance while keeping inference costs affordable compared with other inference-time algorithms. Overall, ICPO provides a principled understanding of self-reflection in LLMs and yields practical benefits for test-time scaling for mathematical reasoning.

cs.LG↗

arXiv2026

Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning

We study online adversarial imitation learning (AIL), where an agent learns from offline expert demonstrations and interacts with the environment online without access to rewards. Despite strong empirical results, the benefits of online interaction and the impact of stochasticity remain poorly understood. We address these gaps by introducing a model-based AIL algorithm (MB-AIL) and establish its horizon-free, second-order sample-complexity guarantees under general function approximations for both expert data and reward-free interactions. These second-order bounds provide an instance-dependent result that can scale with the variance of returns under the relevant policies and therefore tighten as the system approaches determinism. Together with second-order, information-theoretic lower bounds on a newly constructed hard-instance family, we show that MB-AIL attains minimax-optimal sample complexity for online interaction (up to logarithmic factors) with limited expert demonstrations and matches the lower bound for expert demonstrations in terms of the dependence on horizon $H$, precision $ε$ and the policy variance $σ^2$. Experiments further validate our theoretical findings and demonstrate that a practical implementation of MB-AIL matches or surpasses the sample efficiency of existing methods.

cs.LG↗

arXiv2026

Imitation from Observations with Trajectory-Level Generative Embeddings

We consider the offline imitation learning from observations (LfO) where the expert demonstrations are scarce and the available offline suboptimal data are far from the expert behavior. Many existing distribution-matching approaches struggle in this regime because they impose strict support constraints and rely on brittle one-step models, making it hard to extract useful signal from imperfect data. To tackle this challenge, we propose TGE, a trajectory-level generative embedding for offline LfO that constructs a dense, smooth surrogate reward by estimating expert state density in the latent space of a temporal diffusion model trained on offline trajectory data. By leveraging the smooth geometry of the learned diffusion embedding, TGE captures long-horizon temporal dynamics and effectively bridges the gap between disjoint supports, ensuring a robust learning signal even when offline data is distributionally distinct from the expert. Empirically, the proposed approach consistently matches or outperforms prior offline LfO methods across a range of D4RL locomotion and manipulation benchmarks.

cs.LG↗

arXiv2025

Graph Conditioned Diffusion for Controllable Histopathology Image Generation

Recent advances in Diffusion Probabilistic Models (DPMs) have set new standards in high-quality image synthesis. Yet, controlled generation remains challenging, particularly in sensitive areas such as medical imaging. Medical images feature inherent structure such as consistent spatial arrangement, shape or texture, all of which are critical for diagnosis. However, existing DPMs operate in noisy latent spaces that lack semantic structure and strong priors, making it difficult to ensure meaningful control over generated content. To address this, we propose graph-based object-level representations for Graph-Conditioned-Diffusion. Our approach generates graph nodes corresponding to each major structure in the image, encapsulating their individual features and relationships. These graph representations are processed by a transformer module and integrated into a diffusion model via the text-conditioning mechanism, enabling fine-grained control over generation. We evaluate this approach using a real-world histopathology use case, demonstrating that our generated data can reliably substitute for annotated patient data in downstream segmentation tasks. The code is available here.

cs.CV↗