Prompt-based learning has emerged as a parameter-efficient finetuning (PEFT) approach to facilitate Large Language Model (LLM) adaptation to downstream tasks by conditioning generation with task-aware guidance. Despite its successes, current prompt-based learning methods heavily rely on laborious grid searching for optimal prompt length and typically require considerable number of prompts, introducing additional computational burden. Worse yet, our pioneer findings indicate that the task-aware prompt design is inherently limited by its absence of instance-aware information, leading to a subtle attention interplay with the input sequence. In contrast, simply incorporating instance-aware information as a part of the guidance can enhance the prompt-tuned model performance without additional fine-tuning. Moreover, we find an interesting phenomenon, namely "attention anchor", that incorporating instance-aware tokens at the earliest position of the sequence can successfully preserve strong attention to critical structural information and exhibit more active attention interaction with all input tokens. In light of our observation, we introduce Capsule Prompt-Tuning (CaPT), an efficient and effective solution that leverages off-the-shelf, informative instance semantics into prompt-based learning. Our approach innovatively integrates both instance-aware and task-aware information in a nearly parameter-free manner (i.e., one single capsule prompt). Empirical results demonstrate that our method can exhibit superior performance across various language tasks (e.g., 84.03\% average accuracy on T5-Large), serving as an "attention anchor," while enjoying high parameter efficiency (e.g., 0.003\% of model parameters on Llama3.2-1B).

While large language models (LLMs) have demonstrated remarkable capabilities in language modeling, recent studies reveal that they often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training. Here, we aim to mitigate such spurious correlations through causality-aware post-training (CAPT). By decomposing a biased prediction into two unbiased steps, known as \textit{event estimation} and \textit{event intervention}, we reduce LLMs' pre-training biases without incurring additional fine-tuning biases, thus enhancing the model's generalization ability. Experiments on the formal causal inference benchmark CLadder and the logical reasoning dataset PrOntoQA show that 3B-scale language models fine-tuned with CAPT can outperform both traditional SFT and larger LLMs on in-distribution (ID) and OOD tasks using only 100 ID fine-tuning samples, demonstrating the effectiveness and sample efficiency of CAPT.

Effectively handling the co-occurrence of non-IID data and long-tailed distributions remains a critical challenge in federated learning. While fine-tuning vision-language models (VLMs) like CLIP has shown to be promising in addressing non-IID data challenges, this approach leads to severe degradation of tail classes in federated long-tailed scenarios. Under the composite effects of strong non-IID data distribution and long-tailed class imbalances, VLM fine-tuning may even fail to yield any improvement. To address this issue, we propose Class-Aware Prompt Learning for Federated Long-tailed Learning (CAPT), a novel framework that leverages a pre-trained VLM to effectively handle both data heterogeneity and long-tailed distributions. CAPT introduces a dual-prompt mechanism that synergizes general and class-aware prompts, enabling the framework to capture global trends while preserving class-specific knowledge. To better aggregate and share knowledge across clients, we introduce a heterogeneity-aware client clustering strategy that groups clients based on their data distributions, enabling efficient collaboration and knowledge sharing. Extensive experiments on various long-tailed datasets with different levels of data heterogeneity demonstrate that CAPT significantly improves tail class performance without compromising overall accuracy, outperforming state-of-the-art methods in federated long-tailed learning scenarios.

Motion planning against sensor data is often a critical bottleneck in real-time robot control. For sampling-based motion planners, which are effective for high-dimensional systems such as manipulators, the most time-intensive component is collision checking. We present a novel spatial data structure, the collision-affording point tree (CAPT): an exact representation of point clouds that accelerates collision-checking queries between robots and point clouds by an order of magnitude, with an average query time of less than 10 nanoseconds on 3D scenes comprising thousands of points. With the CAPT, sampling-based planners can generate valid, high-quality paths in under a millisecond, with total end-to-end computation time faster than 60 FPS, on a single thread of a consumer-grade CPU. We also present a point cloud filtering algorithm, based on space-filling curves, which reduces the number of points in a point cloud while preserving structure. Our approach enables robots to plan at real-time speeds in sensed environments, opening up potential uses of planning for high-dimensional systems in dynamic, changing, and unmodeled environments.

The ability to estimate joint parameters is essential for various applications in robotics and computer vision. In this paper, we propose CAPT: category-level articulation estimation from a point cloud using Transformer. CAPT uses an end-to-end transformer-based architecture for joint parameter and state estimation of articulated objects from a single point cloud. The proposed CAPT methods accurately estimate joint parameters and states for various articulated objects with high precision and robustness. The paper also introduces a motion loss approach, which improves articulation estimation performance by emphasizing the dynamic features of articulated objects. Additionally, the paper presents a double voting strategy to provide the framework with coarse-to-fine parameter estimation. Experimental results on several category datasets demonstrate that our methods outperform existing alternatives for articulation estimation. Our research provides a promising solution for applying Transformer-based architectures in articulated object analysis.

The construction of open-domain dialogue systems requires high-quality dialogue datasets. The dialogue data admits a wide variety of responses for a given dialogue history, especially responses with different semantics. However, collecting high-quality such a dataset in most scenarios is labor-intensive and time-consuming. In this paper, we propose a data augmentation method to automatically augment high-quality responses with different semantics by counterfactual inference. Specifically, given an observed dialogue, our counterfactual generation model first infers semantically different responses by replacing the observed reply perspective with substituted ones. Furthermore, our data selection method filters out detrimental augmented responses. Experimental results show that our data augmentation method can augment high-quality responses with different semantics for a given dialogue history, and can outperform competitive baselines on multiple downstream tasks.

Hollywood's Captain Kirk, 90-year-old William Shatner, blasted into space Wednesday in a convergence of science fiction and science reality, reaching the final frontier aboard a ship built by Jeff Bezos' Blue Origin company. The "Star Trek" actor and three fellow passengers hurtled to an altitude of 66.5 miles over the West Texas desert in the fully automated capsule, then safely parachuted back to Earth. The flight lasted just over 10 minutes. "What you have given me is the most profound experience," an exhilarated Shatner told Bezos after climbing out the hatch, the words spilling from him in a soliloquy almost as long as the flight. "I hope I never recover from this. I hope that I can maintain what I feel now. I don't want to lose it."

Hollywood's Captain Kirk, 90-year-old William Shatner, blasted into space Wednesday in a convergence of science fiction and science reality, reaching the final frontier aboard a ship built by Jeff Bezos' Blue Origin company. The "Star Trek" hero and three fellow passengers hurtled to an estimated 66 miles (106 kilometers) over the West Texas desert in the fully automated capsule, then safely parachuted back to Earth in a flight that lasted just over 10 minutes. ""You have done something," an exhilarated Shatner told Bezos as he emerged from the capsule, the words spilling from him in a torrent. "What you have given me is the most profound experience." He added: "I hope I never recover from this." He said that going from the blue sky to the blackness of space was a moving experience that made him wonder, "Is that the way death is?" Shatner became the oldest person in space, eclipsing the previous record -- set by a passenger on a similar jaunt on a Bezos spaceship in July -- by eight years. The flight included about three minutes of weightlessness and a view of the curvature of the Earth. Sci-fi fans reveled in the opportunity to see the man best known as the stalwart Capt. James T. Kirk of the starship Enterprise boldly go where no star of American TV has gone before. "This is a pinch-me moment for all of us to see Capt.

VAN HORN, Texas (AP) -- Hollywood's Captain Kirk, 90-year-old William Shatner, blasted into space Wednesday in a convergence of science fiction and science reality, reaching the final frontier aboard a ship built by Jeff Bezos' Blue Origin company. The "Star Trek" hero and three fellow passengers hurtled to an estimated 66 miles (106 kilometers) over the West Texas desert in the fully automated capsule, then safely parachuted back to Earth in a flight that lasted just over 10 minutes. "You have done something," an exhilarated Shatner told Bezos as he emerged from the capsule, the words spilling from him in a torrent. "What you have given me is the most profound experience." He added: "I hope I never recover from this."

Michael Kanaan, AI and machine learning in suicide prevention … He is currently the director of operations for Air Force / MIT artificial intelligence.