29 accepted papers
The interaction of robots with bendable objects in midair presents significant challenges in control, often resulting in performance degradation and potential crashes, especially for aerial robots due to their limited actuation capabilities and constant need to remain airborne. This paper presents a…
High-quality kernel is critical for scalable AI systems, and enabling LLMs to generate such code would advance AI development. However, training LLMs for this task requires sufficient data, a robust environment, and the process is often vulnerable to _reward hacking_ and _lazy optimization_. In thes…
Efficient deployment of deep neural networks increasingly relies on Post-Training Quantization (PTQ). Logarithmic PTQ, in particular, promises multiplier-free hardware efficiency, but its performance is often limited by the nonlinear and symmetric quantization grid and standard rounding-to-nearest (…
Adaptive rounding techniques in Post-Training Quantization (PTQ) enable the efficient deployment of Large Language Models (LLMs) with low resource and data dependencies. While learning-based rounding methods are accurate yet costly, compensation-based approaches offer a highly efficient alternative.…
Masked diffusion language models decode by iteratively unmasking tokens, where the unmasking order defines an ``order of thought'' that strongly influences generation quality yet is typically chosen heuristically. We derive a tractable upper bound on the sequential decoding mismatch, measured by the…
Reinforcement Learning for Large Language Models (LLMs) often suffers from training collapse in long-horizon tasks due to exploding gradient variance. To mitigate this, baseline is commonly introduced for advantage computation; however, traditional value models remain difficult to optimize, and stan…
Policy gradient methods for Large Language Models (LLMs) optimize a policy $\pi_\theta$ via a surrogate objective computed from samples of a rollout policy $\pi_{\text{roll}}$. However, modern LLM-RL pipelines suffer from unavoidable implementation divergences—such as backend discrepancies, Mixture-…
Modeling and rendering dynamic urban driving scenes is crucial for self-driving simulation. Current high-quality methods typically rely on costly manual object tracklet annotations, while self-supervised approaches fail to capture dynamic object motions accurately and decompose scenes properly, resu…
Real-world datasets collected from sensors or human inputs are prone to noise and errors, posing significant challenges for applying offline reinforcement learning (RL). While existing methods have made progress in addressing corrupted actions and rewards, they remain insufficient for handling corru…
The interaction of robots with bendable objects in midair presents significant challenges in control, often resulting in performance degradation and potential crashes, especially for aerial robots due to their limited actuation capabilities and constant need to remain airborne. This letter presents
An interesting behavior in large language models (LLMs) is prompt sensitivity. When provided with different but semantically equivalent versions of the same prompt, models may produce very different distributions of answers. This suggests that the uncertainty reflected in a model's output distributi…
Advancements in Large Language Models (LLMs) and their increasing use in medical question-answering necessitate rigorous evaluation of their reliability. A critical challenge lies in hallucination, where models generate plausible yet factually incorrect outputs. In the medical domain, this poses ser
Efficient energy management and scalability are critical for aerial robots in tasks such as pickup-and-delivery and surveillance. This paper introduces MochiSwarm, an open-source testbed of light-weight micro robotic blimps designed for multi-robot operation without external localization. We propose
The flexible gripper exhibits limited load capacity while possessing dexterity and adaptability to complex environments. Conversely, the thermally-driven variable stiffness gripper boasts high load capacity but suffers from slow response times. This study presents a multifunctional flexible gripper
Thompson Sampling is a principled method for balancing exploration and exploitation, but its real-world adoption faces computational challenges in large-scale or non-conjugate settings. While ensemble-based approaches offer partial remedies, they typically require prohibitively large ensemble sizes.…
Learning policy from offline datasets through offline reinforcement learning (RL) holds promise for scaling data-driven decision-making while avoiding unsafe and costly online interactions. However, real-world data collected from sensors or humans often contains noise and errors, posing a significan…
Routine visual inspections of concrete structures are imperative for upholding the safety and integrity of critical infrastructure. Such visual inspections sometimes happen under low-light conditions, e.g., checking for bridge health. Crack segmentation under such conditions is challenging due to th…
Recently, Gaussian splatting has received more and more attention in the field of static scene rendering. Due to the low computational overhead and inherent flexibility of explicit representations, plane-based explicit methods are popular ways to predict deformations for Gaussian-based dynamic scene…
We propose HyperAgent, a reinforcement learning (RL) algorithm based on the hypermodel framework for exploration in RL. HyperAgent allows for the efficient incremental approximation of posteriors associated with an optimal action-value function ($Q^\star$) without the need for conjugacy and follows…
We consider the problem of policy transfer between two Markov Decision Processes (MDPs). We introduce a lemma based on existing theoretical results in reinforcement learning to measure the relativity gap between two arbitrary MDPs, that is the difference between any two cumulative expected returns d…
Data curation is the problem of how to collect and organize samples into a dataset that supports efficient learning. Despite the centrality of the task, little work has been devoted towards a large-scale, systematic comparison of various curation methods. In this work, we take steps towards a formal…
Small soft amphibious robots have the potential to be used in the exploration of underwater pipelines, surface defect detection of underwater equipment, and underwater biological observations. In this study, we developed a small electromagnetically driven soft amphibious robot with inchworm gait mot
Offline reinforcement learning (RL) presents a promising approach for learning reinforced policies from offline datasets without the need for costly or unsafe interactions with the environment. However, datasets collected by humans in real-world environments are often noisy and may even be malicious…
Traditional aerial vehicles have limitations in their capabilities due to actuator constraints, such as motor saturation. The hardware components and their arrangement are designed to satisfy specific requirements and are difficult to modify during operation. To address this problem, we introduce a…
Graph neural networks, which typically exchange information between local neighbors, often struggle to capture long-range interactions (LRIs) within the graph. Building a graph hierarchy via graph pooling methods is a promising approach to address this challenge; however, hierarchical information pr…
We present an aerial vehicle composed of a custom quadrotor with tilted rotors and a helium balloon, called SBlimp. We propose a novel control strategy that takes advantage of the natural stable attitude of the blimp to control translational motion. Different from cascade controllers in the literatu…
Dexterous manipulation of objects through fine control of physical contacts is essential for many important tasks of daily living. A fundamental ability underlying fine contact control is compliant control, i.e., controlling the contact forces while moving. For robots, the most widely explored appro…
We present a design, model, and control for a novel jumping-flying robot that is called PogoDrone. The robot is composed of a quadrotor with a passive mechanism for jumping. The robot can continuously jump in place or fly like a normal quadrotor. Jumping in place allows the robot to quickly move and…
Traditional aerial vehicles are usually custom-designed for specific tasks. Although they offer an efficient solution, they are not always able to adapt to changes in the task specification, e.g., increasing the payload. This applies to quadrotors, having a maximum payload and only four controllable…