arXiv subjects

Jaemoo Choi

Publications and source records attributed to Jaemoo Choi.

At least 19 recordsLinked to original sources

arXiv2026

Multi-Draft On-Policy Distillation for Diffusion Drafters

Speculative decoding is used to reduce the inference cost of language models. One-step diffusion drafters propose a block of multiple tokens in parallel, reducing the sequential cost of speculative decoding. On-policy distillation trains these drafters using verifier feedback on their own proposals. However, parallel drafting makes this feedback difficult to use: the drafter predicts each token without observing the preceding tokens sampled within the same block, while the verifier conditions its prediction on those tokens. Different sampled prefixes therefore give different verifier targets for the same drafter prediction. We show that distilling against these targets separately can suppress tokens that are plausible after some prefixes but unlikely after others, harming draft acceptance. We explain the effects of this mismatch and introduce Multi-Draft On-Policy Distillation (MDraft), a new parallel drafter distillation method which samples several draft blocks from the same context and aggregates the verifier's full-vocabulary conditionals across their prefixes. We use all the drafts to collect information from the verifier, allowing support from alternative prefixes to influence the training target. The resulting algorithm improves the acceptance length of a parallel drafter beyond the level of pre-training, and alleviates the effects of the distributional mismatch. MDraft changes only training, retaining the drafter's architecture and inference procedure, allowing the resulting drafter to be used as-is in place of the pretrained checkpoint. Experiments on a suite of mathematical, coding, and conversational tasks show longer accepted drafts than prior distillation methods.

cs.CL↗

arXiv2026

Efficient Adjoint Matching for Fine-tuning Diffusion Models

Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Among reward-gradient-based methods, Adjoint Matching (AM) provides a principled formulation by casting reward fine-tuning as a stochastic optimal control (SOC) problem. However, AM inevitably requires a substantial computational cost: it requires (i) stochastic simulation of full generative trajectories under memoryless dynamics, resulting in a large number of function evaluations, and (ii) backward ODE simulation of the adjoint state along each sampled trajectory. In this work, we observe that both bottlenecks are closely tied to the non-trivial base drift inherited from the pretrained model. Motivated by this observation, we propose Efficient Adjoint Matching (EAM), which substantially improves training efficiency by reformulating the SOC problem with a linear base drift and a correspondingly modified terminal cost. This reformulation removes both sources of inefficiency; it enables training-time sampling with a few-step deterministic ODE solver and yields a closed-form adjoint solution that eliminates backward adjoint simulation. On standard text-to-image reward fine-tuning benchmarks, EAM converges up to 4x faster than AM and matches or surpasses it across various metrics including PickScore, ImageReward, HPSv2.1, CLIPScore and Aesthetics.

cs.LG↗

arXiv2026

In-Distribution Forcing for Long Video Generation at Test Time

Modern autoregressive (AR) video diffusion models excel at short-horizon video generation, yet generating long videos remains challenging due to drifting, where colors and textures shift, and motion dynamics decay. Existing works primarily rely on KV conditioning, which selects or modifies cached key-value (KV) entries to mitigate drifting. However, we observe that KV conditioning alone is insufficient as it assumes cached KV entries remain in-distribution. This assumption fails beyond the training horizon: nothing constrains the construction of KV entries during rollout, giving rise to the KV-provenance problem where cached entries themselves become out-of-distribution (OOD). To address this, we propose In-Distribution Forcing (ID-Forcing), a test-time framework that aligns both KV caching and KV conditioning with training configurations. Its key mechanism, self-caching, prevents OOD KV entries at their source. Each chunk is cached without attending to prior KV entry, keeping the rolling window exactly in-distribution. Consequently, ID-Forcing seamlessly extends short-horizon models to minute-scale video generation. Extensive evaluations show that our method remains competitive on standard video generation benchmark while substantially outperforming prior work in mitigating drifting, as validated by both our drift metrics and a user study.

cs.CV↗

arXiv2026

Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching

Diffusion models often yield highly curved trajectories and noisy score targets due to an uninformative, memoryless forward process that induces independent data-noise coupling. We propose Adjoint Schrödinger Bridge Matching (ASBM), a generative modeling framework that recovers optimal trajectories in high dimensions via two stages. First, we view the Schrödinger Bridge (SB) forward dynamic as a coupling construction problem and learn it through a data-to-energy sampling perspective that transports data to an energy-defined prior. Then, we learn the backward generative dynamic with a simple matching loss supervised by the induced optimal coupling. By operating in a non-memoryless regime, ASBM produces significantly straighter and more efficient sampling paths. Compared to prior works, ASBM scales to high-dimensional data with notably improved stability and efficiency. Extensive experiments on image generation show that ASBM improves fidelity with fewer sampling steps. We further showcase the effectiveness of our optimal trajectory via distillation to a one-step generator.

cs.CV↗

arXiv2026

Distributionally Robust Schrödinger Bridge

Schrödinger bridge (SB) learns stochastic transport between prescribed initial and target distributions. When the initial distribution shifts at test time, the learned dynamics can fail to recover the target distribution. We introduce the Distributionally Robust Schrödinger Bridge (DRSB), which learns a single controller that accounts for uncertainty in the initial distribution. The DRSB objective consists of control energy and a KL penalty between the resulting terminal distribution and the target distribution. DRSB seeks a single controller that minimizes the worst-case value of this objective as the initial distribution varies within an ambiguity set around the nominal distribution. We derive an exact variational formulation of this objective and connect its fixed-terminal-cost subproblem to stochastic optimal control and distributionally robust optimization. This formulation motivates an alternating algorithm that updates the adversarial initial distribution, estimates the terminal log-density ratio, and trains the controller. We develop Wasserstein and Sinkhorn variants using stochastic control optimality conditions to approximate the gradients required for adversarial updates. Experiments on two-dimensional transport tasks and image-to-image translation show improved robustness to input perturbations relative to standard SB, with a tradeoff in nominal performance. On Gaussian mixture transport, Sinkhorn DRSB also achieves lower mean sliced Wasserstein distance than fixed-level noise augmentation at both tested unseen noise levels.

cs.LG↗

arXiv2026

RMA: Context-Orchestrated Research Math Agents

Long-horizon mathematical reasoning fails less often because a model cannot produce a valid next step than because an agent fails to maintain and expose the right semantic state across many iterations. Left unmanaged, this produces research-level proofs that are locally convincing yet globally incomplete: a key lemma unproved, an assumption unchecked, a citation unsupported, or a computational claim unverified. We present Research Math Agents (RMA), an agentic framework for long-horizon proof development built around a persistent, typed research store and an orchestrator that compiles operation-specific context from that store. The Research Context Orchestrator is the central state-management layer between the persistent research store and each locally scoped proof operation: it retrieves task-relevant artifacts, compiles them into a bounded context, invokes the appropriate operation, and writes the resulting proof edits, issue updates, literature notes, plans, or evaluations back to the store. This process is designed to keep proof revisions, unresolved issues, prior attempts, literature, and evaluations available across rounds while exposing only task-relevant state to each local operation. We evaluate RMA across complementary research-level settings using independent expert evaluation, blind mathematician review, LLM-based benchmark evaluation, and Lean 4 kernel verification. RMA achieves a 42.5% solve rate on the independently evaluated SOOHAK Challenge Hard set, obtains 8 of 10 correct solutions on First Proof B1 and 8 of 10 passing solutions on B2 under human-expert evaluation, and verifies 213 of 300 sampled Research Solved targets in Formal Conjectures with the Lean 4 kernel.

cs.AI↗

arXiv2026

LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation

World models, game simulators, and long-take video creation require coherent scene evolution and sustained dynamics over extended durations. Autoregressive (AR) video diffusion provides a natural framework for long-horizon generation, yet extended rollouts often become near-static or lose visual quality. We hypothesize that these failures reflect the limited guidance provided by short-video supervision on how ongoing scene dynamics develops over longer durations. This motivates us to introduce LongTake, a two-stage training pipeline built around Long-Horizon Teacher Forcing (TF) on curated real long videos. Long-Horizon TF trains the AR model to predict later frames conditioned on long ground-truth video prefixes, extending direct supervision beyond the short training horizon. This supervision is designed to help the model sustain dynamics and preserve visual quality during long-horizon generation. Our central finding is that this training stage strengthens direct initialization for distribution matching distillation (DMD) under student self-rollout, without the intermediate few-step distillation stage used in standard pipelines. Under the same five-second DMD training setup, our initialization yields substantially higher dynamic degree than short horizon TF initialization on 30-second rollouts at comparable aesthetic quality, and surpasses the evaluated baselines in both measures. Hybrid DMD further reuses this teacher to extend supervision to later frames of the self-rollout while retaining bidirectional joint supervision over the initial window. On long-horizon self-rollouts, LongTake lies on the Pareto front of dynamic degree and aesthetic quality, and Hybrid DMD attains the highest dynamic degree among evaluated methods at both 30s and 60s.

cs.CV↗

arXiv2026

Scaling Reinforcement Learning for Diffusion Models via Velocity Matching

Reward-based fine-tuning of diffusion models has largely inherited likelihood-based policy optimization developed for autoregressive large language models (LLMs). Diffusion models, however, are natively trained through velocity regression and do not directly provide the likelihood of a generated sample. Existing methods address this using transition likelihoods along stochastic denoising trajectories or evidence lower bounds (ELBOs) to approximate generated-sample likelihoods. These approximations arise from applying likelihood-based updates to models whose native training and generation operate through velocity fields. We instead take velocity matching as the starting point for reward fine-tuning. We propose \textbf{reward-based velocity matching (RVM)}, which weights the velocity-matching loss by reward with an additional anchor regression term, requiring neither likelihood estimation nor likelihood ratios. RVM recovers Reinforce Adjoint Matching at the update level and contains DiffusionNFT as a special case, while ELBO-based methods are closely related through the same velocity-regression structure. This unified view isolates reward design and anchor velocity as principal design choices in velocity-based fine-tuning. Across text-to-image, text-to-video, and image-to-video generation, RVM matches or outperforms the evaluated trajectory-based methods. On Wan2.1-T2V-1.3B, it achieves the highest VBench Overall among the evaluated methods, with substantially lower estimated training costs than the trajectory-based approaches. For video fine-tuning, we introduce a dynamic-tracking reward that provides explicit motion feedback and improves both Dynamic Degree and overall VBench performance.

cs.CV↗

arXiv2026

QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning

GRPO-style reinforcement learning (RL)-based LLM fine-tuning algorithms have recently gained popularity. Relying on heuristic trust-region approximations, however, they can lead to brittle optimization behavior, as global importance-ratio clipping and group-wise normalization fail to regulate samples whose importance ratios fall outside the clipping range. We propose Query-Adaptive Trust-Region policy Optimization (QUATRO), which directly enforces trust-region constraints through a principled optimization. This yields a clear and interpretable objective that enables explicit control over policy updates and stable, entropy-controlled optimization, with a stabilizer terms arising intrinsically from the exact trust-region formulation. Empirically verified on diverse mathematical reasoning benchmarks, QUATRO shows stable training under increased policy staleness and aggressive learning rates, maintaining well-controlled entropy throughout training.

cs.LG↗

arXiv2026

Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type methods. Existing approaches primarily focus on crafting new objectives built on already heavily engineered LLM objectives, using ad hoc estimators for likelihood, without a thorough investigation into how such estimation affects overall algorithmic performance. In this work, we provide a systematic analysis of the RL design space by disentangling three factors: i) policy-gradient objectives, ii) likelihood estimators, and iii) rollout sampling schemes. We show that adopting an evidence lower bound (ELBO) based model likelihood estimator, computed only from the final generated sample, is the dominant factor enabling effective, efficient, and stable RL optimization, outweighing the impact of the specific policy-gradient loss functional. We validate our findings across multiple reward benchmarks using SD 3.5 Medium, and observe consistent trends across all tasks. Our method improves the GenEval score from 0.24 to 0.95 in 90 GPU hours, which is 4.6 times more efficient than FlowGRPO and $2\times$ more efficient than the SOTA method without reward hacking.

cs.LG↗

arXiv2026

Hard-Constrained Sampling on Embedded Riemannian Manifolds via Adjoint Schrödinger Bridges

A variety of tasks require sampling from unnormalized Boltzmann distributions supported on manifolds. Building upon the foundations of adjoint matching and adjoint Schrödinger bridge sampling, this paper provides a theoretically justified method, through the lens of stochastic optimal control, to address this problem on smooth, compact, path-connected embedded Riemannian manifolds. As an element of novelty compared to existing literature, feasibility is enforced at the level of the state space, meaning the controlled diffusion is defined intrinsically on the curved space. Empirical validations are provided for several physics applications.

eess.SY↗

arXiv2026

Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is crucial to enabling dLLMs to achieve performance comparable to that of AR-LLMs on important tasks, such as reasoning. However, RL algorithms well-suited to dLLMs' unique characteristics have yet to be developed. This paper proposes Distribution Matching Policy Optimization (DMPO), a principled and theoretically grounded RL fine-tuning method specifically designed to enhance the reasoning capabilities of dLLMs by matching the dLLM policy distribution to the optimal, reward-tilted one through cross-entropy optimization. We identify a key implementation challenge with small training batch sizes and propose several effective solutions based on a novel weight baseline subtraction technique. DMPO exhibits superior performance on multiple reasoning benchmarks without supervised fine-tuning, achieving up to a $39.63$ percentage-point improvement in accuracy over prior non-DMPO RL baselines and $67.97$ percentage points over the base model, underscoring the effectiveness of the distribution-matching framework. Our code is available at https://github.com/yuchen-zhu-zyc/DMPO.

cs.LG↗

arXiv2026

Generalized Schrödinger Bridge on Graphs

Transportation on graphs is a fundamental challenge across many domains, where decisions must respect topological and operational constraints. Despite the need for actionable policies, existing graph-transport methods lack this expressivity. They rely on restrictive assumptions, fail to generalize across sparse topologies, and scale poorly with graph size and time horizon. To address these issues, we introduce Generalized Schrödinger Bridge on Graphs (GSBoG), a novel scalable data-driven framework for learning executable controlled continuous-time Markov chain (CTMC) policies on arbitrary graphs under state cost augmented dynamics. Notably, GSBoG learns trajectory-level policies, avoiding dense global solvers and thereby enhancing scalability. This is achieved via a likelihood optimization approach, satisfying the endpoint marginals, while simultaneously optimizing intermediate behavior under state-dependent running costs. Extensive experimentation on challenging real-world graph topologies shows that GSBoG reliably learns accurate, topology-respecting policies while optimizing application-specific intermediate state costs, highlighting its broad applicability and paving new avenues for cost-aware dynamical transport on general graphs.

cs.LG↗

arXiv2026

Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning

Diffusion models provide strong priors for generating structured data, but many tasks require outputs beyond the scale on which these models are typically trained. Compositional generation addresses this by composing overlapping local plans from a pretrained short-horizon prior into a long-horizon output. However, standard composition primarily enforces agreement between neighboring local plans, yielding local consistency without directly specifying the global structure of the full composition. As a result, locally compatible plans may still form an implausible route, task sequence, or temporal evolution. Existing methods improve global coherence by repeatedly propagating local consistency signals or by adding inference-time optimization, but these procedures become expensive as the number or dimensionality of local plans increases. We propose Coarse-to-Fine Compositional Diffusion (CoFi), an inference-time sampler that separates global structure formation from local detail refinement. CoFi first aligns local denoised estimates around a shared coarse structure, producing a global scaffold that captures the long-range task-level arrangement. It then diffuses this scaffold to an intermediate noise level and denoises it with the same pretrained local prior, restoring local fine structure while preserving the scaffold-induced global coherence. Across long-horizon robotic planning, panoramic image generation, and long video generation, CoFi not only improves both global coherence and local sample quality over prior compositional baselines, but also requires 2-8x fewer denoiser evaluations.

cs.RO↗

arXiv2026

MetaDNS: Enhancing Exploration in Discrete Neural Samplers via Well-Tempered Metadynamics

Sampling from discrete distributions with multiple modes and energy barriers is fundamental to machine learning and computational physics. Recent discrete neural samplers like MDNS suffer from mode collapse and fail to sample high-energy barrier regions between modes, which is critical for free energy estimation and understanding phase transitions. We propose Metadynamics Discrete Neural Sampler (MetaDNS), a general framework integrating well-tempered metadynamics into discrete diffusion or autoregressive samplers. By maintaining an adaptive, history-dependent bias potential along selected low-dimensional coordinates, MetaDNS forces exploration of previously inaccessible regions, enabling free energy reconstruction infeasible with standard neural samplers due to a lack of high-energy samples. On challenging low-temperature benchmarks including Ising, Potts, and the copper-gold binary alloy, MetaDNS reproduces the thermodynamic distribution. Compared to MCMC-based metadynamics, MetaDNS also achieves comparable exploration requiring fewer bias deposition steps.

cond-mat.stat-mech↗

arXiv2026

Proximal Diffusion Neural Sampler

The task of learning a diffusion-based neural sampler for drawing samples from an unnormalized target distribution can be viewed as a stochastic optimal control problem on path measures. However, the training of neural samplers can be challenging when the target distribution is multimodal with significant barriers separating the modes, potentially leading to mode collapse. We propose a framework named Proximal Diffusion Neural Sampler (PDNS) that addresses these challenges by tackling the stochastic optimal control problem via proximal point method on the space of path measures. PDNS decomposes the learning process into a series of simpler subproblems that create a path gradually approaching the desired distribution. This staged procedure traces a progressively refined path to the desired distribution and promotes thorough exploration across modes. For a practical and efficient realization, we instantiate each proximal step with a proximal weighted denoising cross-entropy (WDCE) objective. We demonstrate the effectiveness and robustness of PDNS through extensive experiments on both continuous and discrete sampling tasks, including challenging scenarios in molecular dynamics and statistical physics. Our code is available at https://github.com/AlexandreGUO2001/PDNS.

cs.LG↗

arXiv2026

Discrete Adjoint Schrödinger Bridge Sampler

Learning discrete neural samplers is challenging due to the lack of gradients and combinatorial complexity. While stochastic optimal control (SOC) and Schrödinger bridge (SB) provide principled solutions, efficient SOC solvers like adjoint matching (AM), which excel in continuous domains, remain unexplored for discrete spaces. We bridge this gap by revealing that the core mechanism of AM is $\mathit{state}\text{-}\mathit{space~agnostic}$, and introduce $\mathbf{discrete~ASBS}$, a unified framework that extends AM and adjoint Schrödinger bridge sampler (ASBS) to discrete spaces. Theoretically, we analyze the optimality conditions of the discrete SB problem and its connection to SOC, identifying a necessary cyclic group structure on the state space to enable this extension. Empirically, discrete ASBS achieves competitive sample quality with significant advantages in training efficiency and scalability.

stat.ML↗

arXiv2026

Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan

We address the convergence problem in learning the Optimal Transport (OT) map, where the OT Map refers to a map from one distribution to another while minimizing the transport cost. Semi-dual Neural OT, a widely used approach for learning OT Maps with neural networks, often generates fake solutions that fail to transfer one distribution to another accurately. We identify a sufficient condition under which the max-min solution of Semi-dual Neural OT recovers the true OT Map. Moreover, to address cases when this sufficient condition is not satisfied, we propose a novel method, OTP, which learns both the OT Map and the Optimal Transport Plan, representing the optimal coupling between two distributions. Under sharp assumptions on the distributions, we prove that our model eliminates the fake solution issue and correctly solves the OT problem. Our experiments show that the OTP model recovers the optimal transport map where existing methods fail and outperforms current OT-based models in image-to-image translation tasks. Notably, the OTP model can learn stochastic transport maps when deterministic OT Maps do not exist, such as one-to-many tasks like colorization.

cs.LG↗