Tsung-Wei Ke

Tsung-Wei Ke, Jyh-Jing Hwang, Yunhui Guo et al.

Unsupervised semantic segmentation aims to discover groupings within and across images that capture object and view-invariance of a category without external supervision. Grouping naturally has levels of granularity, creating ambiguity in unsupervised segmentation. Existing methods avoid this ambiguity and treat it as a factor outside modeling, whereas we embrace it and desire hierarchical grouping consistency for unsupervised segmentation. We approach unsupervised segmentation as a pixel-wise feature learning problem. Our idea is that a good representation shall reveal not just a particular level of grouping, but any level of grouping in a consistent and predictable manner. We enforce spatial consistency of grouping and bootstrap feature learning with co-segmentation among multiple views of the same image, and enforce semantic consistency across the grouping hierarchy with clustering transformers between coarse- and fine-grained features. We deliver the first data-driven unsupervised hierarchical semantic segmentation method called Hierarchical Segment Grouping (HSG). Capturing visual similarity and statistical co-occurrences, HSG also outperforms existing unsupervised segmentation methods by a large margin on five major object- and scene-centric benchmarks. Our code is publicly available at https://github.com/twke18/HSG .

Tsung-Wei Ke, Sangwoo Mo, Stella X. Yu

Large vision and language models learned directly through image-text associations often lack detailed visual substantiation, whereas image segmentation tasks are treated separately from recognition, supervisedly learned without interconnections. Our key observation is that, while an image can be recognized in multiple ways, each has a consistent part-and-whole visual organization. Segmentation thus should be treated not as an end task to be mastered through supervised learning, but as an internal process that evolves with and supports the ultimate goal of recognition. We propose to integrate a hierarchical segmenter into the recognition process, train and adapt the entire model solely on image-level recognition objectives. We learn hierarchical segmentation for free alongside recognition, automatically uncovering part-to-whole relationships that not only underpin but also enhance recognition. Enhancing the Vision Transformer (ViT) with adaptive segment tokens and graph pooling, our model surpasses ViT in unsupervised part-whole discovery, semantic segmentation, image classification, and efficiency. Notably, our model (trained on unlabeled 1M ImageNet images) outperforms SAM (trained on 11M images and 1 billion masks) by absolute 8% in mIoU on PartImageNet object segmentation.

Mihir Prabhudesai, Tsung-Wei Ke, Alexander C. Li et al.

The advancements in generative modeling, particularly the advent of diffusion models, have sparked a fundamental question: how can these models be effectively used for discriminative tasks? In this work, we find that generative models can be great test-time adapters for discriminative models. Our method, Diffusion-TTA, adapts pre-trained discriminative models such as image classifiers, segmenters and depth predictors, to each unlabelled example in the test set using generative feedback from a diffusion model. We achieve this by modulating the conditioning of the diffusion model using the output of the discriminative model. We then maximize the image likelihood objective by backpropagating the gradients to discriminative model's parameters. We show Diffusion-TTA significantly enhances the accuracy of various large-scale pre-trained discriminative models, such as, ImageNet classifiers, CLIP models, image pixel labellers and image depth predictors. Diffusion-TTA outperforms existing test-time adaptation methods, including TTT-MAE and TENT, and particularly shines in online adaptation setups, where the discriminative model is continually adapted to each example in the test set. We provide access to code, results, and visualizations on our website: https://diffusion-tta.github.io/.

Chiensheng Chiang, Kuan-Hsun Tu, Jia-Wei Liao et al.

We introduce COT-FM, a general framework that reshapes the probability path in Flow Matching (FM) to achieve faster and more reliable generation. FM models often produce curved trajectories due to random or batchwise couplings, which increase discretization error and reduce sample quality. COT-FM fixes this by clustering target samples and assigning each cluster a dedicated source distribution obtained by reversing pretrained FM models. This divide-and-conquer strategy yields more accurate local transport and significantly straighter vector fields, all without changing the model architecture. As a plug-and-play approach, COT-FM consistently accelerates sampling and improves generation quality across 2D datasets, image generation benchmarks, and robotic manipulation tasks.

Tsung-Wei Ke, Nikolaos Gkanatsios, Katerina Fragkiadaki

Diffusion policies are conditional diffusion models that learn robot action distributions conditioned on the robot and environment state. They have recently shown to outperform both deterministic and alternative action distribution learning formulations. 3D robot policies use 3D scene feature representations aggregated from a single or multiple camera views using sensed depth. They have shown to generalize better than their 2D counterparts across camera viewpoints. We unify these two lines of work and present 3D Diffuser Actor, a neural policy equipped with a novel 3D denoising transformer that fuses information from the 3D visual scene, a language instruction and proprioception to predict the noise in noised 3D robot pose trajectories. 3D Diffuser Actor sets a new state-of-the-art on RLBench with an absolute performance gain of 18.1% over the current SOTA on a multi-view setup and an absolute gain of 13.1% on a single-view setup. On the CALVIN benchmark, it improves over the current SOTA by a 9% relative increase. It also learns to control a robot manipulator in the real world from a handful of demonstrations. Through thorough comparisons with the current SOTA policies and ablations of our model, we show 3D Diffuser Actor's design choices dramatically outperform 2D representations, regression and classification objectives, absolute attentions, and holistic non-tokenized 3D scene embeddings.

Tsung-Wei Ke, Jyh-Jing Hwang, Stella X. Yu

Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, labeled points and scribbles. This task is challenging, as coarse annotations (tags, boxes) lack precise pixel localization whereas sparse annotations (points, scribbles) lack broad region coverage. Existing methods tackle these two types of weak supervision differently: Class activation maps are used to localize coarse labels and iteratively refine the segmentation model, whereas conditional random fields are used to propagate sparse labels to the entire image. We formulate weakly supervised segmentation as a semi-supervised metric learning problem, where pixels of the same (different) semantics need to be mapped to the same (distinctive) features. We propose 4 types of contrastive relationships between pixels and segments in the feature space, capturing low-level image similarity, semantic annotation, co-occurrence, and feature affinity They act as priors; the pixel-wise feature can be learned from training images with any partial annotations in a data-driven fashion. In particular, unlabeled pixels in training images participate not only in data-driven grouping within each image, but also in discriminative feature learning within and across images. We deliver a universal weakly supervised segmenter with significant gains on Pascal VOC and DensePose. Our code is publicly available at https://github.com/twke18/SPML.

Brian Yang, Huangyuan Su, Nikolaos Gkanatsios et al.

Diffusion models excel at modeling complex and multimodal trajectory distributions for decision-making and control. Reward-gradient guided denoising has been recently proposed to generate trajectories that maximize both a differentiable reward function and the likelihood under the data distribution captured by a diffusion model. Reward-gradient guided denoising requires a differentiable reward function fitted to both clean and noised samples, limiting its applicability as a general trajectory optimizer. In this paper, we propose DiffusionES, a method that combines gradient-free optimization with trajectory denoising to optimize black-box non-differentiable objectives while staying in the data manifold. Diffusion-ES samples trajectories during evolutionary search from a diffusion model and scores them using a black-box reward function. It mutates high-scoring trajectories using a truncated diffusion process that applies a small number of noising and denoising steps, allowing for much more efficient exploration of the solution space. We show that DiffusionES achieves state-of-the-art performance on nuPlan, an established closed-loop planning benchmark for autonomous driving. Diffusion-ES outperforms existing sampling-based planners, reactive deterministic or diffusion-based policies, and reward-gradient guidance. Additionally, we show that unlike prior guidance methods, our method can optimize non-differentiable language-shaped reward functions generated by few-shot LLM prompting. When guided by a human teacher that issues instructions to follow, our method can generate novel, highly complex behaviors, such as aggressive lane weaving, which are not present in the training data. This allows us to solve the hardest nuPlan scenarios which are beyond the capabilities of existing trajectory optimization methods and driving policies.

Yash Jangir, Yidi Zhang, Kashu Yamazaki et al.

The pursuit of robot generalists - instructable agents capable of performing diverse tasks across diverse environments - demands rigorous and scalable evaluation. Yet real-world testing of robot policies remains fundamentally constrained: it is labor-intensive, slow, unsafe at scale, and difficult to reproduce. Existing simulation benchmarks are similarly limited, as they train and test policies within the same synthetic domains and cannot assess models trained from real-world demonstrations or alternative simulation environments. As policies expand in scope and complexity, these barriers only intensify, since defining "success" in robotics often hinges on nuanced human judgments of execution quality. In this paper, we introduce a new benchmarking framework that overcomes these challenges by shifting VLA evaluation into large-scale simulated environments augmented with online human feedback. Leveraging advances in vision-language models, 2D-to-3D generative modeling, and differentiable rendering, our approach automatically converts video demonstrations from widely used robot datasets into simulated counterparts. Within these digital twins, we assess VLA policies using both automated VLM-guided scoring and scalable human preference judgments collected from crowdworkers, transforming human involvement from tedious scene setup, resetting, and safety supervision into lightweight preference comparisons. To measure robustness, we systematically perturb simulated environments along multiple axes, such as textures and object placements, stress-testing policy generalization under controlled variation. The result is a continuously evolving, reproducible, and scalable benchmark for real-world trained robot manipulation policies, addressing a critical missing capability in today's robotics landscape.

Chih Yao Hu, Yang-Sen Lin, Yuna Lee et al.

We present See, Point, Fly (SPF), a training-free aerial vision-and-language navigation (AVLN) framework built atop vision-language models (VLMs). SPF is capable of navigating to any goal based on any type of free-form instructions in any kind of environment. In contrast to existing VLM-based approaches that treat action prediction as a text generation task, our key insight is to consider action prediction for AVLN as a 2D spatial grounding task. SPF harnesses VLMs to decompose vague language instructions into iterative annotation of 2D waypoints on the input image. Along with the predicted traveling distance, SPF transforms predicted 2D waypoints into 3D displacement vectors as action commands for UAVs. Moreover, SPF also adaptively adjusts the traveling distance to facilitate more efficient navigation. Notably, SPF performs navigation in a closed-loop control manner, enabling UAVs to follow dynamic targets in dynamic environments. SPF sets a new state of the art in DRL simulation benchmark, outperforming the previous best method by an absolute margin of 63%. In extensive real-world evaluations, SPF outperforms strong baselines by a large margin. We also conduct comprehensive ablation studies to highlight the effectiveness of our design choice. Lastly, SPF shows remarkable generalization to different VLMs. Project page: https://spf-web.pages.dev

Jhen Hsieh, Kuan-Hsun Tu, Kuo-Han Hung et al.

We present DexMan, an automated framework that converts human visual demonstrations into bimanual dexterous manipulation skills for humanoid robots in simulation. Operating directly on third-person videos of humans manipulating rigid objects, DexMan eliminates the need for camera calibration, depth sensors, scanned 3D object assets, or ground-truth hand and object motion annotations. Unlike prior approaches that consider only simplified floating hands, it directly controls a humanoid robot and leverages novel contact-based rewards to improve policy learning from noisy hand-object poses estimated from in-the-wild videos. DexMan achieves state-of-the-art performance in object pose estimation on the TACO benchmark, with absolute gains of 0.08 and 0.12 in ADD-S and VSD. Meanwhile, its reinforcement learning policy surpasses previous methods by 19% in success rate on OakInk-v2. Furthermore, DexMan can generate skills from both real and synthetic videos, without the need for manual data collection and costly motion capture, and enabling the creation of large-scale, diverse datasets for training generalist dexterous manipulation.

Djengo Cyun-Jyun Fang, Tsung-Wei Ke

Explicit information seeking is essential to human problem-solving in practical environments characterized by incomplete information and noisy dynamics. When the true environmental state is not directly observable, humans seek information to update their internal dynamics and inform future decision-making. Although existing Large Language Model (LLM) planning agents have addressed observational uncertainty, they often overlook discrepancies between their internal dynamics and the actual environment. We introduce Information Seeking Decision Planner (InfoSeeker), an LLM decision-making framework that integrates task-oriented planning with information seeking to align internal dynamics and make optimal decisions under uncertainty in both agent observations and environmental dynamics. InfoSeeker prompts an LLM to actively gather information by planning actions to validate its understanding, detect environmental changes, or test hypotheses before generating or revising task-oriented plans. To evaluate InfoSeeker, we introduce a novel benchmark suite featuring partially observable environments with incomplete observations and uncertain dynamics. Experiments demonstrate that InfoSeeker achieves a 74% absolute performance gain over prior methods without sacrificing sample efficiency. Moreover, InfoSeeker generalizes across LLMs and outperforms baselines on established benchmarks such as robotic manipulation and web navigation. These findings underscore the importance of tightly integrating planning and information seeking for robust behavior in partially observable environments. The project page is available at https://infoseekerllm.github.io

Jyh-Jing Hwang, Tsung-Wei Ke, Jianbo Shi et al.

Pixel-wise losses, e.g., cross-entropy or L2, have been widely used in structured prediction tasks as a spatial extension of generic image classification or regression. However, its i.i.d. assumption neglects the structural regularity present in natural images. Various attempts have been made to incorporate structural reasoning mostly through structure priors in a cooperative way where co-occurring patterns are encouraged. We, on the other hand, approach this problem from an opposing angle and propose a new framework, Adversarial Structure Matching (ASM), for training such structured prediction networks via an adversarial process, in which we train a structure analyzer that provides the supervisory signals, the ASM loss. The structure analyzer is trained to maximize the ASM loss, or to emphasize recurring multi-scale hard negative structural mistakes among co-occurring patterns. On the contrary, the structured prediction network is trained to reduce those mistakes and is thus enabled to distinguish fine-grained structures. As a result, training structured prediction networks using ASM reduces contextual confusion among objects and improves boundary localization. We demonstrate that our ASM outperforms pixel-wise IID loss or structural prior GAN loss on three different structured prediction tasks: semantic segmentation, monocular depth estimation, and surface normal prediction.

Tsung-Wei Ke, Jyh-Jing Hwang, Ziwei Liu et al.

Semantic segmentation has made much progress with increasingly powerful pixel-wise classifiers and incorporating structural priors via Conditional Random Fields (CRF) or Generative Adversarial Networks (GAN). We propose a simpler alternative that learns to verify the spatial structure of segmentation during training only. Unlike existing approaches that enforce semantic labels on individual pixels and match labels between neighbouring pixels, we propose the concept of Adaptive Affinity Fields (AAF) to capture and match the semantic relations between neighbouring pixels in the label space. We use adversarial learning to select the optimal affinity field size for each semantic category. It is formulated as a minimax problem, optimizing our segmentation neural network in a best worst-case learning scenario. AAF is versatile for representing structures as a collection of pixel-centric relations, easier to train than GAN and more efficient than CRF without run-time inference. Our extensive evaluations on PASCAL VOC 2012, Cityscapes, and GTA5 datasets demonstrate its above-par segmentation performance and robust generalization across domains.

Tsung-Wei Ke, Michael Maire, Stella X. Yu

We propose a multigrid extension of convolutional neural networks (CNNs). Rather than manipulating representations living on a single spatial grid, our network layers operate across scale space, on a pyramid of grids. They consume multigrid inputs and produce multigrid outputs; convolutional filters themselves have both within-scale and cross-scale extent. This aspect is distinct from simple multiscale designs, which only process the input at different scales. Viewed in terms of information flow, a multigrid network passes messages across a spatial pyramid. As a consequence, receptive field size grows exponentially with depth, facilitating rapid integration of context. Most critically, multigrid structure enables networks to learn internal attention and dynamic routing mechanisms, and use them to accomplish tasks on which modern CNNs fail. Experiments demonstrate wide-ranging performance advantages of multigrid. On CIFAR and ImageNet classification tasks, flipping from a single grid to multigrid within the standard CNN paradigm improves accuracy, while being compute and parameter efficient. Multigrid is independent of other architectural choices; we show synergy in combination with residual connections. Multigrid yields dramatic improvement on a synthetic semantic segmentation dataset. Most strikingly, relatively shallow multigrid networks can learn to directly perform spatial transformation tasks, where, in contrast, current CNNs fail. Together, our results suggest that continuous evolution of features on a multigrid pyramid is a more powerful alternative to existing CNN designs on a flat grid.

Tsung-Yu Lin, Tsung-Wei Ke, Tyng-Luh Liu

We address the problem of converting large-scale high-dimensional image data into binary codes so that approximate nearest-neighbor search over them can be efficiently performed. Different from most of the existing unsupervised approaches for yielding binary codes, our method is based on a dimensionality-reduction criterion that its resulting mapping is designed to preserve the image relationships entailed by the inner products of sparse codes, rather than those implied by the Euclidean distances in the ambient space. While the proposed formulation does not require computing any sparse codes, the underlying computation model still inevitably involves solving an unmanageable eigenproblem when extremely high-dimensional descriptors are used. To overcome the difficulty, we consider the column-sampling technique and presume a special form of rotation matrix to facilitate subproblem decomposition. We test our method on several challenging image datasets and demonstrate its effectiveness by comparing with state-of-the-art binary coding techniques.