Related papers: Implicit Action Chunking for Smooth Continuous Con…
Omnimodal large language models (OmniLLMs) jointly process audio and visual streams, but the resulting long multimodal token sequences make inference prohibitively expensive. Existing compression methods typically rely on fixed window…
Reinforcement learning in discrete combinatorial action spaces requires searching over exponentially many joint actions to simultaneously select multiple sub-actions that form coherent combinations. Existing approaches either simplify…
Designing traffic-smoothing cruise controllers that can be deployed onto autonomous vehicles is a key step towards improving traffic flow, reducing congestion, and enhancing fuel efficiency in mixed autonomy traffic. We bypass the common…
Among approaches for provably safe reinforcement learning, Model Predictive Shielding (MPS) has proven effective at complex tasks in continuous, high-dimensional state spaces, by leveraging a backup policy to ensure safety when the learned…
Accurately modeling wind turbine wakes is essential for optimizing wind farm performance but remains a persistent challenge. While the dynamic wake meandering (DWM) model captures unsteady wake behavior, it suffers from near-wake…
This paper presents a safety-critical reinforcement learning framework for nonlinear dynamical systems with continuous state and input spaces operating under explicit physical constraints. Hard safety constraints are enforced independently…
Action chunking is widely used in generative visuomotor policies, yet the recurring execution discontinuities at chunk boundaries still lack a mechanistic explanation. This paper treats chunk-boundary artifact as an analyzable mechanism…
Detecting actions in videos is an important yet challenging task. Previous works usually utilize (a) sliding window paradigms, or (b) per-frame action scoring and grouping to enumerate the possible temporal locations. Their performances are…
Specifying robotic manipulation tasks in a manner that is both expressive and precise remains a central challenge. While visual goals provide a compact and unambiguous task specification, existing goal-conditioned policies often struggle…
In this paper, we introduce a consistency-driven dual LSTM framework for accurately learning both the forward and inverse kinematics of a pneumatically actuated soft robotic arm integrated into a wearable device. This approach effectively…
Keyword Spotting (KWS) from speech signals is widely applied to perform fully hands-free speech recognition. The KWS network is designed as a small-footprint model so it can continuously be active. Recent efforts have explored dynamic…
Previous deep learning-based event denoising methods mostly suffer from poor interpretability and difficulty in real-time processing due to their complex architecture designs. In this paper, we propose window-based event denoising, which…
Editing faces in videos is a popular yet challenging aspect of computer vision and graphics, which encompasses several applications including facial attractiveness enhancement, makeup transfer, face replacement, and expression manipulation.…
Randomized smoothing is a general technique for computing sample-dependent robustness guarantees against adversarial attacks for deep classifiers. Prior works on randomized smoothing against L_1 adversarial attacks use additive smoothing…
Interactive video segmentation models such as SAM2 have demonstrated strong generalization across diverse visual domains. However, under weak user supervision, for example, when sparse point prompts are provided on a single frame, their…
There has been renewed recent interest in developing effective lower bounds for Dynamic Time Warping (DTW) distance between time series. These have many applications in time series indexing, clustering, forecasting, regression and…
To segment a signal into blocks to be analyzed, few-shot keyword spotting (KWS) systems often utilize a sliding window of fixed size. Because of the varying lengths of different keywords or their spoken instances, choosing the right window…
Long-term temporal credit assignment is an important challenge in deep reinforcement learning (RL). It refers to the ability of the agent to attribute actions to consequences that may occur after a long time interval. Existing…
The ubiquity of sequences in many domains enhances significant recent interest in sequence learning, for which a basic problem is how to measure the distance between sequences. Dynamic time warping (DTW) aligns two sequences by nonlinear…
Reinforcement learning in discrete-continuous hybrid action spaces presents fundamental challenges for robotic manipulation, where high-level task decisions and low-level joint-space execution must be jointly optimized. Existing approaches…