Recent advancements in multimodal large language models (MLLMs) have opened new avenues for video understanding. However, achieving high fidelity in zero-shot video tasks remains challenging. Traditional video processing methods rely heavily on fine-tuning to capture nuanced spatial-temporal details, which incurs significant data and computation costs. In contrast, training-free approaches, though efficient, often lack robustness in preserving context-rich features across complex video content. To this end, we propose DYTO, a novel dynamic token merging framework for zero-shot video understanding that adaptively optimizes token efficiency while preserving crucial scene details. DYTO integrates a hierarchical frame selection and a bipartite token merging strategy to dynamically cluster key frames and selectively compress token sequences, striking a balance between computational efficiency with semantic richness. Extensive experiments across multiple benchmarks demonstrate the effectiveness of DYTO, achieving superior performance compared to both fine-tuned and training-free methods and setting a new state-of-the-art for zero-shot video understanding.

Heterogeneous Graph Neural Networks (HGNNs) have achieved promising results in various heterogeneous graph learning tasks, owing to their superiority in capturing the intricate relationships and diverse relational semantics inherent in heterogeneous graph structures. However, the neighborhood-fetching latency incurred by structure dependency in HGNNs makes it challenging to deploy for latency-constrained applications that require fast inference. Inspired by recent GNN-to-MLP knowledge distillation frameworks, we introduce HG2M and HG2M+ to combine both HGNN's superior performance and MLP's efficient inference. HG2M directly trains student MLPs with node features as input and soft labels from teacher HGNNs as targets, and HG2M+ further distills reliable and heterogeneous semantic knowledge into student MLPs through reliable node distillation and reliable meta-path distillation. Experiments conducted on six heterogeneous graph datasets show that despite lacking structural dependencies, HG2Ms can still achieve competitive or even better performance than HGNNs and significantly outperform vanilla MLPs. Moreover, HG2Ms demonstrate a 379.24$\times$ speedup in inference over HGNNs on the large-scale IGB-3M-19 dataset, showcasing their ability for latency-sensitive deployments.

The emergence of generative artificial intelligence (GAI) and large language models (LLMs) such ChatGPT has enabled the realization of long-harbored desires in software and robotic development. The technology however, has brought with it novel ethical challenges. These challenges are compounded by the application of LLMs in other machine learning systems, such as multi-robot systems. The objectives of the study were to examine novel ethical issues arising from the application of LLMs in multi-robot systems. Unfolding ethical issues in GPT agent behavior (deliberation of ethical concerns) was observed, and GPT output was compared with human experts. The article also advances a model for ethical development of multi-robot systems. A qualitative workshop-based method was employed in three workshops for the collection of ethical concerns: two human expert workshops (N=16 participants) and one GPT-agent-based workshop (N=7 agents; two teams of 6 agents plus one judge). Thematic analysis was used to analyze the qualitative data. The results reveal differences between the human-produced and GPT-based ethical concerns. Human experts placed greater emphasis on new themes related to deviance, data privacy, bias and unethical corporate conduct. GPT agents emphasized concerns present in existing AI ethics guidelines. The study contributes to a growing body of knowledge in context-specific AI ethics and GPT application. It demonstrates the gap between human expert thinking and LLM output, while emphasizing new ethical concerns emerging in novel technology.

We propose an Economic Lexicon (EL) specifically designed for textual applications in economics. We construct the dictionary with two important characteristics: 1) to have a wide coverage of terms used in documents discussing economic concepts, and 2) to provide a human-annotated sentiment score in the range [-1,1]. We illustrate the use of the EL in the context of a simple sentiment measure and consider several applications in economics. The comparison to other lexicons shows that the EL is superior due to its wider coverage of domain relevant terms and its more accurate categorization of the word sentiment.

This paper presents a study of participants interacting with and using GaMaDHaNi, a novel hierarchical generative model for Hindustani vocal contours. To explore possible use cases in human-AI interaction, we conducted a user study with three participants, each engaging with the model through three predefined interaction modes. Although this study was conducted "in the wild"-- with the model unadapted for the shift from the training data to real-world interaction -- we use it as a pilot to better understand the expectations, reactions, and preferences of practicing musicians when engaging with such a model. We note their challenges as (1) the lack of restrictions in model output, and (2) the incoherence of model output. We situate these challenges in the context of Hindustani music and aim to suggest future directions for the model design to address these gaps.

The rapid advancement of large language models (LLMs) and multimodal learning has transformed digital content creation and manipulation. Traditional visual editing tools require significant expertise, limiting accessibility. Recent strides in instruction-based editing have enabled intuitive interaction with visual content, using natural language as a bridge between user intent and complex editing operations. This survey provides an overview of these techniques, focusing on how LLMs and multimodal models empower users to achieve precise visual modifications without deep technical knowledge. By synthesizing over 100 publications, we explore methods from generative adversarial networks to diffusion models, examining multimodal integration for fine-grained content control. We discuss practical applications across domains such as fashion, 3D scene manipulation, and video synthesis, highlighting increased accessibility and alignment with human intuition. Our survey compares existing literature, emphasizing LLM-empowered editing, and identifies key challenges to stimulate further research. We aim to democratize powerful visual editing across various industries, from entertainment to education. Interested readers are encouraged to access our repository at https://github.com/tamlhp/awesome-instruction-editing.

To control the behavior of language models, steering methods attempt to ensure that outputs of the model satisfy specific pre-defined properties. Adding steering vectors to the model is a promising method of model control that is easier than finetuning, and may be more robust than prompting. However, it can be difficult to anticipate the effects of steering vectors produced by methods such as CAA [Panickssery et al., 2024] or the direct use of SAE latents [Templeton et al., 2024]. In our work, we address this issue by using SAEs to measure the effects of steering vectors, giving us a method that can be used to understand the causal effect of any steering vector intervention. We use this method for measuring causal effects to develop an improved steering method, SAE-Targeted Steering (SAE-TS), which finds steering vectors to target specific SAE features while minimizing unintended side effects. We show that overall, SAE-TS balances steering effects with coherence better than CAA and SAE feature steering, when evaluated on a range of tasks.

Large Language Models (LLMs) excel at understanding the semantic relationships between queries and documents, even with lengthy and complex long-tail queries. These queries are challenging for feedback-based rankings due to sparse user engagement and limited feedback, making LLMs' ranking ability highly valuable. However, the large size and slow inference of LLMs necessitate the development of smaller, more efficient models (sLLMs). Recently, integrating ranking label generation into distillation techniques has become crucial, but existing methods underutilize LLMs' capabilities and are cumbersome. Our research, RRADistill: Re-Ranking Ability Distillation, propose an efficient label generation pipeline and novel sLLM training methods for both encoder and decoder models. We introduce an encoder-based method using a Term Control Layer to capture term matching signals and a decoder-based model with a ranking layer for enhanced understanding. A/B testing on a Korean-based search platform, validates the effectiveness of our approach in improving re-ranking for long-tail queries.

At a wide desk in a bedroom somewhere sits a figure, her back facing the camera, supported by an ergonomic white office chair. Her head is bracketed by puffy, white noise-cancelling headphones. Her wrists rest on a foam cloud as she plays a pixelated farm-simulation video game called Stardew Valley on a handheld Nintendo Switch. She is surrounded by screens. On the wall, lights the shape of geometric tiles cast a soft glow in changing colors according to whatever is onscreen.

A Google Gemini user reported a shocking answer. 'PLEASE DIE': Google's AI chatbot Gemini is at the center of another controversy after a user reported a shocking answer in a conversation about challenges aging adults face. A graduate student in Michigan was told "please die" by the artificial intelligence chatbot, CBS News first reported. 'LAST TO GO' Ben Affleck is getting a lot of attention for his views on artifical intelligence. Last week, the actor spoke at CNBC's Delivering Alpha 2024 investor summit, taking time to share his thoughts on how AI will affect the entertainment industry.