TodayNewsResearchFieldsStacksMarketAnalytics
⌘K

Research

New papers ranked by attention, with their code, models and discussion linked. Pick a field on the left.

WeekMonthQuarterAll
NewestMost relevant

Papers

Open problems

Rising research topics

Ask the research

Sample
ByteTrail · AI and developer-tools intelligence
NewsResearchStacksAPI

Rising research topics

  • Linear bandits94+42.4%
  • Diffusion priors24+41.2%
  • Quantum machine learning22+29.4%
  • Molecular property prediction46+21.1%
  • Algorithmic trading21+5.0%
  • Channel state information140.0%
  • Federated learning35−7.9%
  • Inference & serving241−9.1%

Open problems across fields

  • Long-video generation with consistent appearance and motion1 paper raises it · 1 addresses it

    Real-time streaming video generation requires maintaining quality and coherence over long sequences without degradation or drift.

    • Wave Forcing: Towards Speed-of-Light Streaming Video Generationraises · addresses
  • LLM research taste alignment with human communities1 paper raises it · 1 addresses it

    LLMs struggle to match human researchers in judging which problems to pursue and methods to try, limiting their utility in research assistance.

    • IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?raises · addresses
  • Cross-repository consistency in coding agents1 paper raises it · 1 addresses it

    Real-world software development often requires coordinated changes across multiple interdependent repositories, which current agents fail to handle reliably.

    • CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agentsraises · addresses
  • Over-proactivity in proactive agents1 paper raises it · 1 addresses it

    Proactive agents often intervene excessively or inappropriately, reducing user trust and effectiveness.

    • HALO: Human-Grounded Granular Evaluation of Proactive Agentsraises · addresses
  • Efficient benchmark prediction with sparse and unpaired data1 paper raises it · 1 addresses it

    Evaluating generative models on all benchmark tasks is costly, and current methods cannot efficiently predict performance from sparse or unpaired responses.

    • Benchmark Prediction with Sparse and Unpaired Cached Responsesraises · addresses

Named by an AI from these papers' abstracts.

Fields · this week
All fields2612Multimodal436Frontier LLMs350Recursive self improvement300Inference & serving241Agents & indirect prompt injection211Neural operators190Clinical reasoning188Robotics156Forecasting time95Linear bandits94Voice AI57AI safety56Molecular property prediction46Federated learning35Character recognition OCR30All 23 fields

Papers

  • arXiv cs.NEOct 6

    ReGraph: A Computational Account of Emergent Generalization in the "what" and "where" Dual Visual Streams

    Hyewon Kang, Jungmin Lee, Ilgyu Lee, Seok-Jun Hong

    Where generalization capacity--the ability to extract context-invariant relational structures--first emerges remains a central question in AI and neuroscience. The foundation for this capacity lies upstream of the hippocampus, within the entorhinal cortex, where parallel pathways dissociate relational structure in the medial entorhinal cortex (MEC) from sensory content in the lateral entorhinal cortex. However, as Eichenbaum argued, such factorization likely originates earlier, driven by the segregation of the dorsal ('where') and ventral ('what') visual streams. Supporting this, grid-like firing patterns--a signature of MEC (context-invariant codes)--also appear in preceding neocortical regions along the dorsal pathway. Yet, how such representations are computationally formed along upstream pathways remains unknown. To investigate this in silico, we developed ReGraph, a recurrent dual-stream graph model with biological inductive biases, including retina-driven stream-specialized encoding, dorsal-to-ventral modulation, and dynamic lateral connectivity. Trained on the action benchmark Something-Something V2, ReGraph revealed a pathway-specific emergence of relational mapping:…

    PDF
  • arXiv cs.CVOct 6

    DensiTok: Making Feed-Forward 3D Gaussian Splatting See More Views Than It Is Given

    Minhyeok Lee, Jungho Lee, Minseok Kang, Heeseung Choi, Ig-Jae Kim +1

    Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across many scenes. Its quality, however, degrades sharply as the number of input images drops. The bottleneck is upstream of the reconstruction heads: from a few unposed views, the internal representation they read carries no evidence for unobserved regions, leaving holes, floaters, and blur. The common remedy supplies that evidence as pixels, synthesizing extra views with an image or video generator and re-encoding them, which is costly and not 3D-consistent by construction. We instead densify the evidence itself. We present DensiTok, a plug-in module for pretrained feed-forward 3DGS models that densifies their internal geometry tokens directly, making a frozen backbone behave as though it had observed many more views than it was given. DensiTok compresses those tokens into a compact latent space, completes the latents of the unobserved viewpoints in a single flow-matching step conditioned on camera geometry, and decodes them back into tokens that the original reconstruction heads. The same module design can be integrated into…

    PDF
  • arXiv cs.CVOct 6

    Revisiting Numerical Forecasting Models for Language-Based Trajectory Prediction

    JunGyu Lee, Inhwan Bae, Hae-Gon Jeon

    Language-based trajectory predictors represent coordinates as discrete tokens and learn auxiliary tasks such as destination and group reasoning. This formulation enables the model to capture behavioral intent and social context beyond coordinate dynamics alone. However, token-level objectives provide only indirect guidance for continuous coordinate-space dynamics. To address this limitation, we introduce MoRE (Mixture of Reward Experts), a refinement framework that transfers numerical forecasting priors into a pretrained language-based predictor through reinforcement learning. Five frozen numerical predictors provide complementary coordinate-level knowledge of motion and interactions. Their predictions are converted into expert rewards and combined through an uncertainty-weighted consensus that penalizes disagreement. A ground-truth reward anchors the prediction to the target trajectory. To focus refinement on difficult cases, MoRE refines the policy using the top 1% of training samples ranked by predictive entropy. Expert predictions are computed once and cached before PPO training, so the experts are not run during policy updates or inference. In this way, MoRE combines the…

    PDF
  • arXiv cs.AIOct 6

    Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents

    Brendan King, Farima Fatahi Bayat, Jean-Flavien Bussotti, Pouya Pezeshkpour, Estevam Hruschka

    When using an LLM agent in a consequential domain, making an informed decision about whether to trust its output or intervene requires calibrated confidence in the agent's success. Confidence estimation for agents is difficult because evidence about success is distributed across heterogeneous, interdependent steps of an agent's trajectory. Practical agentic deployments introduce further challenges: frontier LLMs often provide limited access to internal signals, agent roll-outs are costly, and training data may be unavailable or quickly become outdated. To address these challenges, we introduce Confidence Reasoning Graphs (CRGs), an inference-time framework that estimates the probability an agent accomplished its task from a single trajectory, without privileged model access or training data. Rather than compressing an execution into a single holistic judgment, a CRG begins with the claim that the agent accomplished its task, decomposes it into contextualized sub-claims grounded in trajectory evidence, estimates confidence for each terminal claim, and finally aggregates these into an overall confidence estimate. Across three agentic benchmarks, three backbone models, and three…

    PDF
  • arXiv cs.ROOct 6

    Adapting Vision-Language-Action Models to Unknown Visual Disruptions During Execution

    Ahin Lee, Jinwoo Seo, Youngsoo Jang, Taesik Gong

    Visual disruptions can arise while a robot is executing a task, leaving a vision-language-action (VLA) policy to respond without knowing the disruption type or timing. We introduce Self-supervised Adaptation from Leftover Trajectories (SALT), which uses the leftover trajectory, the unexecuted part of the previous action chunk, as self-supervision for test-time adaptation. Because consecutive chunks overlap in time, the leftover provides a temporally aligned target for the current prediction over the same future control interval. At the onset of a visual shift, the leftover can retain a plan formed before the corruption, so updating the policy toward it anchors the adaptation across the shift (Transition Anchoring). SALT keeps the adapted policy and regenerates the current chunk, whose leftover becomes the target at the next replan, carrying the correction forward along the execution trajectory (Sequential Correction Propagation). Supervision comes entirely from the policy's own predictions, requiring no disruption annotations, expert actions, or target-domain demonstrations, and a lightweight adaptation gate calibrated only on nominal trajectories decides when updates begin. On…

    PDF
  • arXiv cs.GROct 6

    UltraDiff: Differentiable Ray Tracing in Ultrasound for Shape Optimization

    Felix Duelmer, Magdalena Wysocki, Nassir Navab, Mohammad Farid Azampour

    Physically-based differentiable rendering enables gradient-based optimization of scene parameters by matching rendered images to measurements, but has so far mainly focused on light transport. We extend this paradigm to medical ultrasound, where image formation resembles transient rendering: echoes are binned by time-of-flight rather than projected onto an image plane. We present UltraDiff, a modular framework for differentiable ultrasound ray tracing. UltraDiff formulates ultrasound image formation as a path-space integral, gated by travel time between the transducer and tissue interfaces, and derives a Monte Carlo estimator of both the forward model and its gradients with respect to scene parameters. We demonstrate this on an inverse geometry estimation: starting from a sphere, an SDF is optimized until simulated echoes match measured ones, recovering vertebral surfaces from simulated B-mode sweeps and from a real robotic acquisition of a spine phantom. Unlike state-of-the-art ultrasound shape reconstruction methods, which rely on pre-segmented images, our approach operates unsupervised on B-mode images through analysis-by-synthesis, while achieving competitive geometric…

    PDF
  • arXiv cs.CLOct 6

    Hybrid Latent Attention for Looped Language Models

    Yuhan Chen, Siyuan Zhang, Nan Wang, Feiyang Kang, Ruoxi Jia

    Looped language models apply the same stack of layers T times to each token, which deepens the model without adding parameters but multiplies its key-value (KV) cache by T. The larger cache limits how many sequences a GPU can decode at once and slows each decoding step, which reads the whole cache. We propose Hybrid Latent Attention (HLA), which keeps exact keys and values within a sliding window of W recent tokens and stores each older token as a compact latent that the query of each loop reads directly, without reconstructing keys and values. We uptrain HLA on Ouro looped models (T=4) with 1.4B and 2.6B parameters, keeping the pretrained weights frozen and training only the added parameters to reproduce the original attention. The cache shrinks by 10.7x per token, fitting 4.0-8.8x as many concurrent sequences per GPU, and decoding throughput improves by 2.5x at 1K-token contexts and by up to 7.4x at 16K. HLA retains over 97% of the original accuracy on math, knowledge and reasoning benchmarks, and 96-100% on long-context retrieval up to 16K tokens. After supervised fine-tuning, it performs on par with the fine-tuned original model on competition-level math.

    PDF
  • arXiv cs.NEOct 6

    Energy-Efficient Spiking Neural Networks for Sensing-Aided Beam Prediction

    Nhan Thanh Nguyen, Phuong Nam Tran, Mengyuan Ma, Huy T. Nguyen, Ahmed Alkhateeb +1

    Sensing-aided beam prediction can reduce the beam-training overhead of millimeter-wave (mmWave) systems by leveraging environmental information from complementary modalities such as vision and position. However, the resulting sensing and inference pipeline can be energy-intensive, motivating the use of energy-efficient spiking neural networks (SNNs) as an alternative to conventional artificial neural networks (ANNs). In this work, we develop SNN architectures for beam prediction and systematically compare them with ANNs using position-only, vision-only, and multimodal inputs. Our results show that compact ANNs consistently outperform SNNs for position-only sensing. In contrast, for vision and multimodal sensing, SNNs achieve higher accuracy than ANNs at similar energy costs and require up to an order of magnitude less energy at a comparable accuracy. For example, the multimodal SNN achieves 58.08% top-1 accuracy, outperforming the closest-energy ANN by 18.11 percentage points. We further show that SNN accuracy is limited by the binary communication between layers rather than by model size. These results demonstrate the potential of SNNs for energy-efficient sensing-aided beam…

    PDF
  • arXiv cs.CVOct 6

    CCDF: A Benchmark Dataset for Deepfake Detection in Real-World Surveillance Footage

    Baptiste Chopin, Thomas Swearingen, Arun Ross, Antitza Dantcheva, Christian Rathgeb

    Due to rapid advances in Generative AI, commercial video generation tools can be used to produce fabricated surveillance footage that can fool both human viewers and automated synthetic video detectors. Since these tools are so widely accessible, a malicious user can create a harmful video clip at minimal cost. The production and dissemination of such videos in high-stakes settings, such as crime reporting and elections, can misdirect emergency response efforts or distort political discourse. Existing deepfake video datasets, used by the research community to develop deepfake detection algorithms, exhibit two limitations: (1) they emphasize benign web content rather than footage of possibly malicious activity, and (2) they rely on older or open-source generators that do not represent recent advances in generative systems. We assemble CCtv DeepFakes (CCDF), a video deepfake dataset, to address both gaps. CCDF contains 1840 videos (460 real and 1380 generated) spanning 16 crime and accident categories, with generated content produced using three leading commercial systems: Grok Imagine, Google VEO 3.1, and OpenAI Sora 2. CCDF is a highly realistic, small-scale, manually annotated…

    PDF
  • arXiv cs.LGOct 6

    Generalized Matheron Variational Implicit Processes

    Luis A. Ortega, Andrés R. Masegosa, Thomas D. Nielsen

    Implicit-process priors specify distributions over functions through sample-forward mechanisms such as Bayesian neural networks and stochastic simulators, but their function-space densities are typically unavailable. We introduce Generalized Matheron Variational Implicit Processes (GMVIP), a pathwise variational family for posterior inference with such priors. For Gaussian-process priors, GMVIP recovers the standard inducing-variable variational GP construction; for general implicit priors, its empirical covariance construction preserves the prior mean and covariance in the population limit. GMVIP constructs posterior samples by drawing a function from the prior and applying a correction anchored at a set of inducing inputs. The effect of this correction away from the inducing inputs is determined directly from prior samples, allowing the posterior to retain the structure and variability of the original implicit process. The (surrogate) prior and variational posterior use the same pathwise construction and differ only in the distribution of whitened inducing coefficients, yielding a tractable coefficient-space Kullback-Leibler divergence. Experiments on regression,…

    PDF
  • arXiv cs.CLOct 6

    Leveraging a four-quadrant approach for evaluating Redpine Science

    Filip Dorm, Leonora Vesterbacka

    Redpine Science gives models and agents a single access point to a wide range of peer-reviewed literature, queried directly through the Model Context Protocol (MCP) and an API. This report evaluates Redpine Science on two levels: the relevance of the retrieved chunks, and a model's answer when it has access to Redpine Science compared to web search. Both public and expert-validated benchmarks are used. Public benchmarks are a widely accepted way to test model development and are comparable across labs, but risk saturation and memorization. To address this, we complement them with an expert-validated question set. In total, this report presents four evaluations. On ScholarQABench SciFact, the public answer-quality benchmark reported here, an agent with Redpine Science answers 94.4% of claims correctly against 87.6% with no retrieval. On the expert-validated question set, an agent with Redpine Science states 80.1% of the required claims against 70.2% for an agent restricted to web search. On the 668 queries of a public retrieval benchmark whose gold paper Redpine holds, stripped of any model reasoning, Redpine Science places the correct source paper in its top ten results for 83.1%…

    PDF
  • arXiv cs.CLOct 6

    Pseudowords as probes: Large Language Models show little of the sublexical sensitivity that governs human pseudoword processing

    Jing Chen, Giulia Loca, Simona Amenta, Marco Marelli

    Systematicity, the probabilistic mapping of form to meaning, permeates language at all levels, and sublexical cues have been shown to govern human pseudoword processing. Yet whether LLMs exhibit comparable sensitivity to these cues remains unclear. We tested five LLMs on two Italian two-alternative forced-choice pseudoword experiments and compared their responses with a human behavioural baseline. LLMs aligned more reliably with humans when real-word options provided a lexical familiarity cue than in the pseudoword-only condition, where they fell substantially below fastText, a character-n-gram model. In addition, the sublexical cosine-similarity cue that reliably drove human--fastText agreement did not consistently transfer to human--LLM alignment, and reasoning-token expenditure bore no consistent relation to human processing difficulty. These findings suggest that LLMs do not necessarily share the sublexical cues that govern human pseudoword processing; we discuss tokenization and training-data coverage as candidate explanations.

    PDF
  • arXiv cs.AIOct 6

    SIGMA: Self-Improving Alignment Generalization from a Model Spec

    Jingyu Zhang, Shruti Palaskar, Daniel Khashabi, Benjamin Van Durme, Leon A. Gatys +1

    LLM agents are increasingly capable of executing complex tasks and of recursively improving themselves on easy-to-verify objectives such as software engineering and mathematics. Since alignment is much harder to verify, this creates a growing risk of capabilities increasing without appropriate safety alignment, especially as capabilities expand to auto-research and cybersecurity. Existing approaches focus on capability self-improvement using verifiable feedback or on alignment training with supervision from stronger models or curated data, creating an external supervision bottleneck for alignment. We ask whether current models can improve their own safety alignment, and propose SIGMA, a data generation and training pipeline enabling alignment self-improvement that generalizes to out-of-distribution settings. Given only a "Model Spec" stating the model's desired behavior, SIGMA leverages a model's reasoning capabilities to strengthen its own safety reasoning. SIGMA first performs spec-guided task synthesis, using the candidate model as a task designer agent to generate diverse alignment dilemma scenarios and convert them into training tasks that stress-test its understanding of…

    PDF
  • arXiv cs.CVOct 6

    Dynamic Alignment and Calibration for Multimodal Learning

    Jinghao Xu, Zhenhua Guo, Xiaofeng Zhu, Xiaoshuang Shi

    Dynamic multimodal learning aims to learn robust representations by adaptively modeling information discrepancies across modalities. However, existing methods still suffer from two limitations: (i) static cross-modal alignment strategies usually impose uniform constraints on all samples while overlooking sample-wise variations, potentially leading to unreasonable over-alignment; and (ii) confidence- or uncertainty-aware fusion methods often fail to adequately account for feature magnitude and confidence differences across modalities. For modality pairs with significant feature magnitude differences or small confidence gaps, it might be unreliable to strictly align fusion weights according to confidence. To address these issues, we propose an Alignment- and Calibration-driven Multimodal Learning framework (ACML). Specifically, ACML incorporates a dynamic cross-modal triplet alignment module, which enforces strong semantic consistency for high-confidence positive pairs while encouraging diverse representation learning between high- and low-confidence positive pairs according to their confidence gaps. Additionally, ACML introduces a difference-aware attention calibration strategy…

    PDF
  • arXiv cs.CVOct 6

    TF-PRVR: Training-Free Partially Relevant Video Retrieval

    Giyeol Kim, Chanho Eom

    Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos containing moments relevant to a given text query. Despite recent progress, existing PRVR methods suffer from two key limitations: a fixed video decomposition scheme that causes semantic dilution, and source-domain overfitting induced by task-specific training. In this paper, we propose TF-PRVR, the first training-free framework for PRVR. TF-PRVR leverages frozen vision-language features to construct video-specific hierarchical representations. It derives temporal semantic signals from frame-level features and applies frequency-based multi-scale analysis to identify adaptive temporal boundaries, producing hierarchical segments with coherent event-level semantics. Built on these segments, TF-PRVR constructs a unified multi-scale graph and propagates query relevance across temporally and semantically related nodes. A moment-aware scoring strategy then aggregates temporally aligned relevance across scales, emphasizing consistently supported moments while suppressing isolated false responses. Without task-specific training, TF-PRVR preserves the general-purpose alignment capability of pre-trained…

    PDF
  • arXiv cs.ROOct 6

    OpenWAM: An Open Framework for Composable World-Action Models

    Heng Yu, David D. Yuan, Juze Zhang, Changan Chen, Yao Feng +5

    World-action models (WAMs) couple future prediction with robot control, yet existing systems often vary the video backbone, interaction structure, supervision, and inference procedure simultaneously, making their design choices difficult to compare. We introduce OPENWAM, an open world-action modeling framework built around a common causal robot-video foundation and configurable video-action interaction. Starting from Wan2.2-5B, we perform causal robot-video pretraining on over 10,000 hours of video, then integrate an action expert through a shared Mixture-of-Transformers architecture that supports joint, video-then-action, action-then-video, and decoupled generation. OPENWAM achieves high success rates on four LIBERO suites and real-world bimanual tasks; robot-video training with causal adaptation improves VTA success on LIBERO-Long from 68.4% to 97.8%. The same configurable architecture naturally extends to inverse and forward dynamics, allowing us to study how counterfactual transitions improve independently trained dynamics models beyond demonstrations alone. When only the video predictor is adapted to a new task, a frozen local-context inverse dynamics model trained on…

    PDF
  • arXiv cs.GROct 6

    Physics-based Sphere Packing for Lagrangian Mesh Morphing

    Jiong Lin, Hod Lipson

    This paper studies tetrahedral meshes as the body representation for differentiable simulation and computational design. Fixed-connectivity meshes degrade under large morphs, while remeshing from scratch discards node correspondence. We present JamTet, a physics-based sphere-packing framework for volumetric meshing and morphing. We contribute (i) a GPU-parallel mesher combining octree-hierarchical packing with constrained Delaunay tetrahedralization, producing more uniform element volumes than TetGen and fTetWild; (ii) Lagrangian mesh morphing that preserves interior-node identities by re-equilibrating the same spheres within changing shapes and rebuilding the boundary and connectivity, remaining inversion-free where fixed-connectivity and TetSphere meshes invert; and (iii) a differentiable GPU simulator in JAX, with mass-spring edges and a volumetric Neo-Hookean term, integrated with mesh morphing in a design pipeline. In soft-robot morphology design experiments, interior-node gradients improve swimming fitness by 0.73-1.07 over a matched surface-only variant, while voxelized versions of the same designs yield 32-63% lower fitness. These results establish sphere packing as a…

    PDF
  • arXiv cs.CVOct 6

    Can We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation Localization

    Xuekang Zhu, Kaiwen Feng, Ruifeng Wang, Xiwen Wang, Xiaochen Ma +8

    Image Manipulation Localization (IML) is commonly formulated as a fully supervised learning task that estimates the optimal manipulation mask $y$ for a given image $x$. In this work, we first reveal the latent nature of artifacts and thus reinterpret IML as a latent-variable problem, $P(y|x)=\int P(y|z)\,P(z|x)\,dz$, where $z$ denotes the artifacts. Following this interpretation, we pinpoint the cause for the current IML models' insufficiency as their implicit artifacts modeling strategy, highlighting the necessity of modeling $z$ in an explicit manner. Without direct labels, feature disentanglement is the most appropriate solution for this explicit modeling. Accordingly, we propose a two-stage learning paradigm with the Pairwise Artifacts Learning (PAL) and Standard Localization (SL) phases to estimate $P(z|x)$ and $P(y|z)$ via edit relations. To support our edit-relation-based learning, we further curate EditGroup-45K, a source-anchored dataset organized into edit groups for pair construction. Extensive experiments show that our PAL paradigm yields consistent improvements across diverse IML architectures, and empirical analyses further verify that PAL does capture artifacts…

    PDF
  • arXiv cs.CVOct 6

    Multimodal Knowledge Distillation for Gastric Adenocarcinoma Classification from Whole-Slide Images

    Shrihari Dumbre, Bikash Santra

    Gastric adenocarcinoma (GA) is a leading cause of cancer-related mortality worldwide, and accurate histopathological subtype classification from whole-slide images (WSIs) is essential for effective treatment planning. While multimodal approaches that integrate pathology report text with WSIs can improve classification, existing methods often depend on computationally expensive transformer architectures and large language models. We propose a multimodal knowledge distillation (MKD) framework that combines a pretrained WSI image encoder and a clinical text encoder using Low-Rank Multimodal Fusion (LMF) to efficiently model cross-modal interactions during training. Each WSI is represented as a bag of patches paired with a slide-level diagnostic caption. The teacher model learns fused image-text representations for subtype classification, while the student model distills this knowledge to enable accurate image-only inference. We evaluate our method on the PatchGastric benchmark dataset and achieve at least 3.35% higher mean accuracy than state-of-the-art approaches, without relying on transformer-based fusion, multi-task learning, or large language models. The source code is…

    PDF
  • arXiv cs.CVOct 6

    Diverse Motion Customization via Control-based Dynamic Optimization

    Youngyoon Choi, Kihyun Kim, Jeongwoo Shin, Joonseok Lee

    Despite recent advances in video generation, motion customization remains challenging due to content leakage, where appearance attributes from the reference video unintentionally propagate into the generated output. We identify this issue as a consequence of the generative process collapsing toward the reference video, which arises from formulating the learning objective as a direct regression on the reference. To address this, we propose Control-based Motion Customization (CMC), a principled training framework that is structurally robust to content leakage. Our key idea is to steer generative dynamics toward desired motion while avoiding collapse toward the reference video, which we formalize using Stochastic Optimal Control (SOC). Under this formulation, customized videos acquire the target motion yet remain within the pre-trained model's prompt-conditional distribution, where appearance is determined by the text prompt rather than the reference video. Furthermore, to improve efficiency, we tailor the SOC formulation to motion customization by eliminating the need for an explicit reward and introducing a timestep-adaptive motion cost that focuses only on early generative…

    PDF
Load more