47 accepted papers
Reverse Kullback–Leibler (KL) divergence-based regularization with respect to a fixed reference policy is widely used in modern reinforcement learning to preserve the desired traits of the reference policy and sometimes to promote exploration (using uniform reference policy, known as entropy regular…
Although retrieval-augmented generation(RAG) significantly improves generation quality by retrieving external knowledge bases and integrating generated content, it faces computational efficiency bottlenecks, particularly in knowledge retrieval tasks involving hierarchical structures for Tree-RAG. Th…
We present Triple Zero Path Planning (TZPP), a collaborative framework for heterogeneous multi-robot systems that requires zero training, zero prior knowledge, and zero simulation. TZPP employs a coordinator–explorer architecture: a humanoid robot handles task coordination, while a quadruped robot e…
An end-to-end monocular 3D recovery framework for Deformable Linear Object (DLO) is proposed in this paper. The fragmented and unreliable 3D point clouds caused by the thin profile and reflective surfaces of DLOs when captured with an RGB-D camera have been a critical challenge in 3D DLO perception.
Large Language Models (LLMs) achieve strong performance on diverse tasks but often exhibit cognitive inertia, struggling to follow instructions that conflict with the standardized patterns learned during supervised fine-tuning (SFT). To evaluate this limitation, we propose Inverse IFEval, a benchmar…
Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which leads to information loss and hallucinations. Recently, mer
Controllable diffusion generation often relies on various heuristics that are seemingly disconnected without a unified understanding. We bridge this gap with Diffusion Controller (DiffCon), a unified control-theoretic view that casts reverse diffusion sampling as state-only stochastic control within…
This paper introduces a novel automatic coverage path planning algorithm for bathymetry surveying with unmanned surface vehicles. The detection range of the mapping sensor employed -- a multibeam echo sounder -- is heavily influenced by local seafloor depths. Hence, a path designed to uniformly cove…
Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks primarily evaluate short-horizon behaviors such as localized code generation, scaffolded completion, or repository repair, leaving it unclear whether agents can sustain coherent re…
Sketch-based solutions are widely used to estimate item frequencies in infinite data streams.Traditional hand-crafted sketches face the bottleneck of further eliminating errors because they cannot fully utilize the data stream distribution.Although recent neural sketches represented by MetaSketch an
While the "deep reasoning" paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling reasoning—reinforcement learning (RL) and instruction distillation --…
The challenge of generating reliable local plans has long hindered practical applications in highly cluttered and dynamic environments. Key fundamental bottlenecks include acquiring large-scale expert demonstrations across diverse scenes and improving learning efficiency with limited data. This pape…
As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI techniques such as unauthorized personalization through Drea
Semi-implicit distributions have shown great promise in variational inference and generative modeling. Hierarchical semi-implicit models, which stack multiple semi-implicit layers, enhance the expressiveness of semi-implicit distributions and can be used to accelerate diffusion models given pret…
Online reinforcement learning (RL) with complex function approximations such as transformers and deep neural networks plays a significant role in the modern practice of artificial intelligence. Despite its popularity and importance, balancing the fundamental trade-off between exploration and exploit…
Recent advances in aligning large language models with human preferences have corroborated the growing importance of best-of-$N$ distillation (BOND). However, the iterative BOND algorithm is prohibitively expensive in practice due to the sample and computation inefficiency. This paper addresses the…
Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-k attention mechanisms have been proposed to accelerate LLM inference…
Multi-agent reinforcement learning (MARL) lies at the heart of a plethora of applications involving the interaction of a group of agents in a shared unknown environment. A prominent framework for studying MARL is Markov games, with the goal of finding various notions of equilibria in a sample-effici…
Transformers have demonstrated remarkable capabilities in multi-step reasoning tasks. However, understandings of the underlying mechanisms by which they acquire these abilities through training remain limited, particularly from a theoretical standpoint. This work investigates how transformers learn…
Reinforcement learning from human feedback (RLHF) has demonstrated great promise in aligning large language models (LLMs) with human preference. Depending on the availability of preference data, both online and offline RLHF are active areas of investigation. A key bottleneck is understanding how to…
Yang et al. (2023) recently showed how to use first-order gradient methods to solve general variational inequalities (VIs) under a limiting assumption that analytic solutions of specific subproblems are available. In this paper, we circumvent this assumption via a warm-starting technique where we s…
A novel RGB-based continuous perception garment classification approach is proposed in this letter, with the aim of identifying the correct category of the garment from a set of categories. It has been observed that treating a video of the continuous deformation of cloth as a set of disordered stati
Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories. In this work, we consider a multi-task setting, in which each agent has its own private reward function corresponding to different tasks, while sharing…
In-context learning (ICL) refers to a remarkable capability of pretrained large language models, which can learn a new task given a few examples during inference. However, theoretical understanding of ICL is largely under-explored, particularly whether transformers can be trained to generalize to un…
In this paper we present a few-shot text-to-video framework LAMP which enables a text-to-image diffusion model to Learn A specific Motion Pattern with 8 16 videos on a single GPU. Unlike existing methods which require a large number of training resources or learn motions that are precisely aligned w…
The Janus Problem is a common issue in SDS-based text-to-3D methods. Due to view encoding approach and 2D diffusion prior guidance, the 3D representation model tends to learn content with higher certainty from each perspective, leading to view inconsistency. In this work, we first model and analyze…
This paper introduces an optimisation-based trajectory deformation and tracking algorithm for tethered differential-driven mobile robots. The motivation of this work is to generate self-entanglement-free (SEF) commands for a tethered differential-driven robot to track a path. Whilst existing path pl…
A generalised solver for the manipulator non-revisiting coverage path planning (NCPP) problem is proposed in this paper. Nonlinear manipulator kinematics and the imposition of task-specific constraints dictate that applying conventional coverage path planning (CPP) solutions based on 2D template mat…
Continuous normalizing flows (CNFs) learn an ordinary differential equation to transform prior samples into data. Flow matching (FM) has recently emerged as a simulation-free approach for training CNFs by regressing a velocity model towards the conditional velocity field. However, on constrained dom…
A novel algorithm to solve the 2D k-shortest non-homotopic path planning (k-SNPP) task is proposed in this paper. The task is of practical significance as a sub-module for higherlevel planning and scheduling tasks, and is gaining increasing attention and focus in recent years. There have existed alg…
Semi-implicit variational inference (SIVI) has been introduced to expand the analytical variational families by defining expressive semi-implicit distributions in a hierarchical manner. However, the single-layer architecture commonly used in current SIVI methods can be insufficient when the target p…
Incorporating a deep generative model as the prior distribution in inverse problems has established substantial success in reconstructing images from corrupted observations. Notwithstanding, the existing optimization approaches use gradient descent largely without adapting to the non-convex nature o…
A novel mechanism to derive self-entanglement-free path for tethered differential-driven robots is proposed in this work. The problem is tailored to the applications of tethered robots without an omni-directional tether re-tractor which is often encountered when an omni-directional tether retracting…
We present a novel framework for 3D object-centric representation learning. Our approach effectively decomposes complex scenes into individual objects from a single image in an unsupervised fashion. This method, called \underline{s}lot-guided \underline{V}olumetric \underline{O}bject \underline{R}ad…
We develop an interior-point approach to solve constrained variational inequality (cVI) problems. Inspired by the efficacy of the alternating direction method of multipliers (ADMM) method in the single-objective context, we generalize ADMM to derive a first-order method for cVIs, that we refer to as…
In this paper, we propose a novel query design for the transformer-based object detection. In previous transformer-based detectors, the object queries are a set of learned embeddings. However, each learned embedding does not have an explicit physical meaning and we cannot explain where it will focu…
In this paper, we propose the first self-distillation framework for general object detection, termed LGD (Label-Guided self-Distillation). Previous studies rely on a strong pretrained teacher to provide instructive knowledge that could be unavailable in real-world scenarios. Instead, we generate an…
An optimal solution to the task-space tracking problem using a non-redundant manipulator is proposed. This is a recurring occurrence in automated manufacturing settings, e.g. welding, deburring, painting, or quality control inspections. Given a pre-defined path for the end-effector to follow, there
One of the valuable directions in feature based SLAM is to parameterize and estimate features accurately. In the real world, closed shape features are especially common. It is necessary to study the feature based SLAM problem on closed shape features. The main contribution of this letter is a 2D las
Object detectors usually achieve promising results with the supervision of complete instance annotations. However, their performance is far from satisfactory with sparse instance annotations. Most existing methods for sparsely annotated object detection either re-weight the loss of hard negative sam…
This work considers the optimal non-revisiting coverage tasks with a single non-redundant manipulator for the case when the object can be positioned at a predefined set of locations within the workcell. The scenario is often encountered in typical industrial settings, for instance when the object pr…
We propose a novel point annotated setting for the weakly semi-supervised object detection task, in which the dataset comprises small fully annotated images and large weakly annotated images by points. It achieves a balance between tremendous annotation burden and detection performance. Based on thi…
This paper revisits feature pyramids networks (FPN) for one-stage detectors and points out that the success of FPN is due to its divide-and-conquer solution to the optimization problem in object detection rather than multi-scale feature fusion. From the perspective of optimization, we introduce an a…
Understanding interactions between humans and objects is one of the fundamental problems in visual classification and an essential step towards detailed scene understanding. Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of com…
A theoretically complete solution to the optimal Non-revisiting Coverage Path Planning (NCPP) problem of any arbitrarily-shaped object with a non-redundant manipulator is proposed in this work. Given topological graphs of surface cells corresponding to feasible and continuous manipulator configurati…
Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better…
We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks. Unlike many previous detectors model anchors via a predefined manner, in MetaAnchor anchor functions could be dynamically generated from the arbitrary customized prior boxes. Taking advantage of weight…