Recurrent neural networks have flourished in many areas. Consequently, we can see new RNN cells being developed continuously, usually by creating or using gates in a new, original way. But what if we told you that gates in RNNs are redundant? In this paper, we propose a new recurrent cell called Residual Recurrent Unit (RRU) which beats traditional cells and does not employ a single gate. It is based on the residual shortcut connection, linear transformations, ReLU, and normalization. To evaluate our cell's effectiveness, we compare its performance against the widely-used GRU and LSTM cells and the recently proposed Mogrifier LSTM on several tasks including, polyphonic music modeling, language modeling, and sentiment analysis. Our experiments show that RRU outperforms the traditional gated units on most of these tasks. Also, it has better robustness to parameter selection, allowing immediate application in new tasks without much tuning.

Intrinsic decomposition is a fundamental mid-level vision problem that plays a crucial role in various inverse rendering and computational photography pipelines. Generating highly accurate intrinsic decompositions is an inherently under-constrained task that requires precisely estimating continuous-valued shading and albedo. In this work, we achieve high-resolution intrinsic decomposition by breaking the problem into two parts. First, we present a dense ordinal shading formulation using a shift- and scale-invariant loss in order to estimate ordinal shading cues without restricting the predictions to obey the intrinsic model. We then combine low- and high-resolution ordinal estimations using a second network to generate a shading estimate with both global coherency and local details. We encourage the model to learn an accurate decomposition by computing losses on the estimated shading as well as the albedo implied by the intrinsic model. We develop a straightforward method for generating dense pseudo ground truth using our model's predictions and multi-illumination data, enabling generalization to in-the-wild imagery. We present an exhaustive qualitative and quantitative analysis of our predicted intrinsic components against state-of-the-art methods. Finally, we demonstrate the real-world applicability of our estimations by performing otherwise difficult editing tasks such as recoloring and relighting.

Large Language Models (LLMs) have garnered significant attention for their powerful ability in natural language understanding and reasoning. In this paper, we present a comprehensive empirical study to explore the performance of LLMs on misinformation detection tasks. This study stands as the pioneering investigation into the understanding capabilities of multiple LLMs regarding both content and propagation across social media platforms. Our empirical studies on five misinformation detection datasets show that LLMs with diverse prompts achieve comparable performance in text-based misinformation detection but exhibit notably constrained capabilities in comprehending propagation structure compared to existing models in propagation-based misinformation detection. Besides, we further design four instruction-tuned strategies to enhance LLMs for both content and propagation-based misinformation detection. These strategies boost LLMs to actively learn effective features from multiple instances or hard instances, and eliminate irrelevant propagation structures, thereby achieving better detection performance. Extensive experiments further demonstrate LLMs would play a better capacity in content and propagation structure under these proposed strategies and achieve promising detection performance. These findings highlight the potential ability of LLMs to detect misinformation.

Are similar, or even identical, mechanisms used in the computational modeling of speech segmentation, serial image processing and music processing? We address this question by exploring how TRACX2, (French et al., 2011; French \& Cottrell, 2014; Mareschal \& French, 2017), a recognition-based, recursive connectionist autoencoder model of chunking and sequence segmentation, which has successfully simulated speech and serial-image processing, might be applied to elementary melody perception. The model, a three-layer autoencoder that recognizes ''chunks'' of short sequences of intervals that have been frequently encountered on input, is trained on the tone intervals of melodically simple French children's songs. It dynamically incorporates the internal representations of these chunks into new input. Its internal representations cluster in a manner that is consistent with ''human-recognizable'' melodic categories. TRACX2 is sensitive to both contour and proximity information in the musical chunks that it encounters in its input. It shows the ''end-of-word'' superiority effect demonstrated by Saffran et al. (1999) for short musical phrases. The overall findings suggest that the recursive autoassociative chunking mechanism, as implemented in TRACX2, may be a general segmentation and chunking mechanism, underlying not only word-and imagechunking, but also elementary melody processing.

Multi-modal Large Language Models (MLLMs) have shown remarkable capabilities in various multi-modal tasks. Nevertheless, their performance in fine-grained image understanding tasks is still limited. To address this issue, this paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. Specifically, we present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. A self-consistent bootstrapping method is also introduced to extend existing dense object annotations into high-quality referring-expression-bounding-box pairs. These methods enable the generation of high-quality instruction data which includes a wide range of fundamental abilities essential for fine-grained image perception. Moreover, we argue that the visual encoder should be tuned during instruction tuning to mitigate the gap between full image perception and fine-grained image perception. Experimental results demonstrate the superior performance of our method. For instance, our model exhibits a 5.2% accuracy improvement over Qwen-VL on GQA and surpasses the accuracy of Kosmos-2 by 24.7% on RefCOCO_val. We also attain the top rank on the leaderboard of MMBench. This promising performance is achieved by training on only publicly available data, making it easily reproducible. The models, datasets, and codes are publicly available at https://github.com/SY-Xuan/Pink.

ABSTRACT We introduce LyricWhiz, a robust, multilingual, and zero-shot automatic lyrics transcription method achieving state-of-the-art performance on various lyrics transcription datasets, even in challenging genres such as rock and metal. In the proposed method, Whisper functions as the "ear" by transcribing the audio, while GPT-4 serves as the "brain," acting as an annotator with a strong performance for contextualized output selection and correction. Our experiments show that LyricWhiz significantly reduces Word Error Rate compared to existing methods in Figure 1. Concept illustration of the working LyricWhiz, English and can effectively transcribe lyrics across multiple where user prompts the two advanced models, Whisper languages. Furthermore, we use LyricWhiz to create and ChatGPT, to perform automatic lyrics transcription.

The ascension of an insider CEO can be a bit underwhelming. When Satya Nadella took the helm of Microsoft in 2014, some employees and investors were disappointed. The search committee had spent months sifting through more than 100 potential leaders, looking for someone who could revive the spirit of innovation that had once defined the company. Along the way, some Wall Street analysts interpreted the fact that no clear external candidate was emerging to indicate that "Microsoft couldn't attract an appealing CEO after years of dwindling relevance," the Wall Street Journal reported. And then, on a frigid January day, they got a 22-year Microsoft veteran as CEO.

Filmmakers have a secret weapon to manipulate our memories and emotions when watching their movies. Researchers found that tunes are strategically placed throughout films to help viewers recall a scene's actions, characters and finale outcomes. The torture of a police officer in Reservoir Dogs is accompanied by the upbeat song'Stuck in the Middle with You' by Stealers Wheel, making it memorable to movie-goers who can recall the violent scene years after. Psychology experts also found the right music is necessary for trailers as filmmakers only have a few minutes to captivate the audience and convince them their movie is worth watching. The torture of a police officer in Reservoir Dogs is accompanied by the upbeat song'Stuck in the Middle with You' by Stealers Wheel, making it memorable to movie-goers who can recall the violent scene years after Libby Damjanovic with Lund University wrote in The Conversation that music is a key part of movies and has become'ingrained in our cinematic experience that we sometimes end up having false memory for it.'

The new interim CEO of OpenAI suggested earlier this year that artificial intelligence holds a level of potential risk for humankind that "should cause you to s**t your pants." Emmett Shear, the co-founder and former CEO of Twitch, was appointed over the weekend to lead OpenAI after its board of directors ousted its longtime CEO Sam Altman in a shock firing on Friday. In a June interview on "The Logan Bartlett Show" podcast, Shear said he feared that AI technology could evolve until it is smart enough to design artificial intelligence on its own, "fully self-improve itself" and outsmart humans. "That kind of intelligence is just an intrinsically very dangerous thing," he said. Human beings are the dominant form of life on this planet, pretty much entirely because we're smarter than the other creatures now."

By the time I sat down with Christopher Nolan in his posh hotel suite not far from the White House, I guessed that he was tired of Washington, D.C. The day before, he'd toured the Oval Office and had lunch on Capitol Hill. Later that night, I'd watched him receive an award from the Federation for American Scientists, an organization that counts Robert Oppenheimer, the subject of Nolan's most recent film, among its founders. He'd endured a joke, repeated too many times by Senate Majority Leader Chuck Schumer, about the subject of his next film--"It's another biopic: Schumer." The award was sitting on an end table next to Nolan, who was dressed in brown slacks, a gray vest, and a navy suit jacket--his Anglo-formality undimmed by decades spent living in Los Angeles. "It's heavy, and glass, and good for self-defense," he said of the award, while filling his teacup.