This project aimed to develop an automated cinematography platform using an unmanned aerial vehicle. Quadcopters are a great platform for shooting aerial scenes but are difficult to maneuver smoothly and can require expertise to pilot. We aim to design an algorithm to enable automated cinematography of a desired object of interest. Given the location of an object and other obstacles in the environment, the drone is able to plan its trajectory while simultaneously keeping the desired object in the video frame and avoiding obstacles. The high maneuverability of quadcopter platforms coupled with the desire for smooth movement and stability from camera platforms means a robust motion planning algorithm must be developed which can take advantage of the quadcopter's abilities while creating motion paths which satisfy the ultimate goal of capturing aerial video. This project aims to research, develop, simulate, and test such an algorithm.

Not everything on the internet is true. This unfortunate fact requires both humans and models to perform complex reasoning about credibility when working with retrieved information. In NLP, this problem has seen little attention. Indeed, retrieval-augmented models are not typically expected to distrust retrieved documents. Human experts overcome the challenge by gathering signals about the context, reliability, and tendency of source documents - that is, they perform source criticism. We propose a novel NLP task focused on finding and summarising such signals. We introduce a new dataset of 6,709 "media background checks" derived from Media Bias / Fact Check, a volunteer-run website documenting media bias. We test open-source and closed-source LLM baselines with and without retrieval on this dataset, finding that retrieval greatly improves performance. We furthermore carry out human evaluation, demonstrating that 1) media background checks are helpful for humans, and 2) media background checks are helpful for retrieval-augmented models.

Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability. However, real function-calling data is quite challenging to collect and annotate, while synthetic data generated by existing pipelines tends to lack coverage and accuracy. In this paper, we present ToolACE, an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data. ToolACE leverages a novel self-evolution synthesis process to curate a comprehensive API pool of 26,507 diverse APIs. Dialogs are further generated through the interplay among multiple agents, guided by a formalized thinking process. To ensure data accuracy, we implement a dual-layer verification system combining rule-based and model-based checks. We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard, rivaling the latest GPT-4 models. Our model and a subset of the data are publicly available at https://huggingface.co/Team-ACE.

If this week's rumor about a video game set in the universe of 2022's The Batman got your hopes up, I have some bad news: no such thing is in development at the moment. Responding to a question on Threads about whether Warner Bros. has a game in the works based on the Robert Pattinson-led film, DC Studios' co-head James Gunn said, "Sadly there is no truth to this whatsoever." The rumor stems from a Puck report that was published on Friday. The Batman, directed by Matt Reeves, popped back up in theaters on Wednesday as part of AMC's celebration of the 85th anniversary of Batman. Work on a sequel is currently underway, and an HBO limited series focusing on The Penguin is slated to come out this fall.

Years before Star Wars, video game designers had begun to explore galactic dogfighting. In 1962, Spacewar!, the first formal computer game, was a rudimentary but influential attempt: two narrow triangles swirled around the gravity well of a star, launching torpedoes at each other. Having established the medium's first principles, hundreds of developers attempted to refine and perfect the genre, which rose and dived in fashion but never fully warped away. Cygni is, perhaps, the highest production attempt yet, a debut from a tiny Scottish studio that answers the improbable question: what if Steven Spielberg had directed Space Invaders? Stylistically reminiscent of the polarity-swapping arcade classic Ikaruga, Cygni is a technological masterclass, your spaceship sweeping over distant robot battlefields, buffeted in the blast of a thousand fireworks.

In 1953, Roald Dahl published "The Great Automatic Grammatizator," a short story about an electrical engineer who secretly desires to be a writer. One day, after completing construction of the world's fastest calculating machine, the engineer realizes that "English grammar is governed by rules that are almost mathematical in their strictness." He constructs a fiction-writing machine that can produce a five-thousand-word short story in thirty seconds; a novel takes fifteen minutes and requires the operator to manipulate handles and foot pedals, as if he were driving a car or playing an organ, to regulate the levels of humor and pathos. The resulting novels are so popular that, within a year, half the fiction published in English is a product of the engineer's invention. Is there anything about art that makes us think it can't be created by pushing a button, as in Dahl's imagination?

This paper introduces the MERIT Dataset, a multimodal (text + image + layout) fully labeled dataset within the context of school reports. Comprising over 400 labels and 33k samples, the MERIT Dataset is a valuable resource for training models in demanding Visually-rich Document Understanding (VrDU) tasks. By its nature (student grade reports), the MERIT Dataset can potentially include biases in a controlled way, making it a valuable tool to benchmark biases induced in Language Models (LLMs). The paper outlines the dataset's generation pipeline and highlights its main features in the textual, visual, layout, and bias domains. To demonstrate the dataset's utility, we present a benchmark with token classification models, showing that the dataset poses a significant challenge even for SOTA models and that these would greatly benefit from including samples from the MERIT Dataset in their pretraining phase.

Large language models (LLMs), such as ChatGPT, have rapidly penetrated into people's work and daily lives over the past few years, due to their extraordinary conversational skills and intelligence. ChatGPT has become the fastest-growing software in terms of user numbers in human history and become an important foundational model for the next generation of artificial intelligence applications. However, the generations of LLMs are not entirely reliable, often producing content with factual errors, biases, and toxicity. Given their vast number of users and wide range of application scenarios, these unreliable responses can lead to many serious negative impacts. This thesis introduces the exploratory works in the field of language model reliability during the PhD study, focusing on the correctness, non-toxicity, and fairness of LLMs from both software testing and natural language processing perspectives. First, to measure the correctness of LLMs, we introduce two testing frameworks, FactChecker and LogicAsker, to evaluate factual knowledge and logical reasoning accuracy, respectively. Second, for the non-toxicity of LLMs, we introduce two works for red-teaming LLMs. Third, to evaluate the fairness of LLMs, we introduce two evaluation frameworks, BiasAsker and XCulturalBench, to measure the social bias and cultural bias of LLMs, respectively.

Adaptive video streaming relies on the construction of efficient bitrate ladders to deliver the best possible visual quality to viewers under bandwidth constraints. The traditional method of content dependent bitrate ladder selection requires a video shot to be pre-encoded with multiple encoding parameters to find the optimal operating points given by the convex hull of the resulting rate-quality curves. However, this pre-encoding step is equivalent to an exhaustive search process over the space of possible encoding parameters, which causes significant overhead in terms of both computation and time expenditure. To reduce this overhead, we propose a deep learning based method of content aware convex hull prediction. We employ a recurrent convolutional network (RCN) to implicitly analyze the spatiotemporal complexity of video shots in order to predict their convex hulls. A two-step transfer learning scheme is adopted to train our proposed RCN-Hull model, which ensures sufficient content diversity to analyze scene complexity, while also making it possible to capture the scene statistics of pristine source videos. Our experimental results reveal that our proposed model yields better approximations of the optimal convex hulls, and offers competitive time savings as compared to existing approaches. On average, the pre-encoding time was reduced by 53.8% by our method, while the average Bjontegaard delta bitrate (BD-rate) of the predicted convex hulls against ground truth was 0.26%, and the mean absolute deviation of the BD-rate distribution was 0.57%.

Given how technology has become the increasingly unstoppable architect of our everyday lives – the world edging closer and closer to a Terminator prequel – it's not hard to immediately invest in a horror film about the all-consuming threat of artificial intelligence. The film industry itself has been losing ground as AI continues to provide a cheaper and easier alternative to those pesky humans and in a year of bleak headline after bleak headline, it should theoretically be perfect timing for Blumhouse's late August M3gan-adjacent chiller AfrAId. Yet, as one might be able to predict without the help of a digital forecast, easy targets are easily missed in a hokey and rushed jumble of half-ideas that's as gimmicky and eye-rollingly stupid as its title. In the dog days of summer, on a particularly rubbishy Labor Day weekend at the movies (other new releases include long-delayed sci-fi thriller Slingshot and a reverential biopic of Reagan), it's at least reassuring to know that very few people will find themselves stuck with this one (it's tracking to make between 5m and 7m). Sony, clearly scared of scaring off those precious few, decided not to provide a single press screening, aware of the critical drubbing this would receive. It's not quite as unreleasably awful as that strategy might suggest – it's competently, at times handsomely, shot, refreshingly dour and crucially not as awful as The Crow – but it's too sloppily written and edited for even the least discerning of horror fans to really enjoy, a patchwork of nonsense confusingly stitched together by someone, who at one point, knew better.