PLAY PODCASTS
Daily Paper Cast

Daily Paper Cast

2,516 episodes — Page 51 of 51

Ep 16Randomized Autoregressive Visual Generation

🤗 Paper Upvotes: 10 | cs.CV Authors: Qihang Yu, Ju He, Xueqing Deng, Xiaohui Shen, Liang-Chieh Chen Title: Randomized Autoregressive Visual Generation Arxiv: http://arxiv.org/abs/2411.00776v1 Abstract: This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The proposed RAR is simple: during a standard autoregressive training process with a next-token prediction objective, the input sequence-typically ordered in raster form-is randomly permuted into different factorization orders with a probability r, where r starts at 1 and linearly decays to 0 over the course of training. This annealing training strategy enables the model to learn to maximize the expected likelihood over all factorization orders and thus effectively improve the model's capability of modeling bidirectional contexts. Importantly, RAR preserves the integrity of the autoregressive modeling framework, ensuring full compatibility with language modeling while significantly improving performance in image generation. On the ImageNet-256 benchmark, RAR achieves an FID score of 1.48, not only surpassing prior state-of-the-art autoregressive image generators but also outperforming leading diffusion-based and masked transformer-based methods. Code and models will be made available at https://github.com/bytedance/1d-tokenizer

Nov 5, 202420 min

Ep 15Survey of User Interface Design and Interaction Techniques in Generative AI Applications

🤗 Paper Upvotes: 8 | cs.HC, cs.AI, cs.CL, cs.LG Authors: Reuben Luera, Ryan A. Rossi, Alexa Siu, Franck Dernoncourt, Tong Yu, Sungchul Kim, Ruiyi Zhang, Xiang Chen, Hanieh Salehy, Jian Zhao, Samyadeep Basu, Puneet Mathur, Nedim Lipka Title: Survey of User Interface Design and Interaction Techniques in Generative AI Applications Arxiv: http://arxiv.org/abs/2410.22370v1 Abstract: The applications of generative AI have become extremely impressive, and the interplay between users and AI is even more so. Current human-AI interaction literature has taken a broad look at how humans interact with generative AI, but it lacks specificity regarding the user interface designs and patterns used to create these applications. Therefore, we present a survey that comprehensively presents taxonomies of how a human interacts with AI and the user interaction patterns designed to meet the needs of a variety of relevant use cases. We focus primarily on user-guided interactions, surveying interactions that are initiated by the user and do not include any implicit signals given by the user. With this survey, we aim to create a compendium of different user-interaction patterns that can be used as a reference for designers and developers alike. In doing so, we also strive to lower the entry barrier for those attempting to learn more about the design of generative AI applications.

Nov 5, 202423 min

Ep 14Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation

🤗 Paper Upvotes: 8 | cs.LG, cs.AI, cs.CL, I.2.6; I.2.7 Authors: Bohan Lyu, Yadi Cao, Duncan Watson-Parris, Leon Bergen, Taylor Berg-Kirkpatrick, Rose Yu Title: Adapting While Learning: Grounding LLMs for Scientific Problems with Intelligent Tool Usage Adaptation Arxiv: http://arxiv.org/abs/2411.00412v1 Abstract: Large Language Models (LLMs) demonstrate promising capabilities in solving simple scientific problems but often produce hallucinations for complex ones. While integrating LLMs with tools can increase reliability, this approach typically results in over-reliance on tools, diminishing the model's ability to solve simple problems through basic reasoning. In contrast, human experts first assess problem complexity using domain knowledge before choosing an appropriate solution approach. Inspired by this human problem-solving process, we propose a novel two-component fine-tuning method. In the first component World Knowledge Distillation (WKD), LLMs learn directly from solutions generated using tool's information to internalize domain knowledge. In the second component Tool Usage Adaptation (TUA), we partition problems into easy and hard categories based on the model's direct answering accuracy. While maintaining the same alignment target for easy problems as in WKD, we train the model to intelligently switch to tool usage for more challenging problems. We validate our method on six scientific benchmark datasets, spanning mathematics, climate science and epidemiology. On average, our models demonstrate a 28.18% improvement in answer accuracy and a 13.89% increase in tool usage precision across all datasets, surpassing state-of-the-art models including GPT-4o and Claude-3.5.

Nov 5, 202420 min

Ep 13In-Context LoRA for Diffusion Transformers

🤗 Paper Upvotes: 7 | cs.CV, cs.GR Authors: Lianghua Huang, Wei Wang, Zhi-Fan Wu, Yupeng Shi, Huanzhang Dou, Chen Liang, Yutong Feng, Yu Liu, Jingren Zhou Title: In-Context LoRA for Diffusion Transformers Arxiv: http://arxiv.org/abs/2410.23775v2 Abstract: Recent research arXiv:2410.15027 has explored the use of diffusion transformers (DiTs) for task-agnostic image generation by simply concatenating attention tokens across images. However, despite substantial computational resources, the fidelity of the generated images remains suboptimal. In this study, we reevaluate and streamline this framework by hypothesizing that text-to-image DiTs inherently possess in-context generation capabilities, requiring only minimal tuning to activate them. Through diverse task experiments, we qualitatively demonstrate that existing text-to-image DiTs can effectively perform in-context generation without any tuning. Building on this insight, we propose a remarkably simple pipeline to leverage the in-context abilities of DiTs: (1) concatenate images instead of tokens, (2) perform joint captioning of multiple images, and (3) apply task-specific LoRA tuning using small datasets (e.g., $20\sim 100$ samples) instead of full-parameter tuning with large datasets. We name our models In-Context LoRA (IC-LoRA). This approach requires no modifications to the original DiT models, only changes to the training data. Remarkably, our pipeline generates high-fidelity image sets that better adhere to prompts. While task-specific in terms of tuning data, our framework remains task-agnostic in architecture and pipeline, offering a powerful tool for the community and providing valuable insights for further research on product-level task-agnostic generation systems. We release our code, data, and models at https://github.com/ali-vilab/In-Context-LoRA

Nov 5, 202420 min

Ep 12Physics in Next-token Prediction

🤗 Paper Upvotes: 7 | cs.LG, cs.AI Authors: Hongjun An, Yiliang Song, Xuelong Li Title: Physics in Next-token Prediction Arxiv: http://arxiv.org/abs/2411.00660v1 Abstract: We discovered the underlying physics in Next-token Prediction (NTP). We identified the law of information conservation within NTP and proposed the First Law of Information Capacity (IC-1), demonstrating that the essence of intelligence emergence in auto-regressive models is fundamentally a process of information transfer. We also introduced Landauer's Principle into NTP, formulating the Second Law of Information Capacity (IC-2), which establishes the relationship between auto-regressive model training and energy consumption. Additionally, we presented several corollaries, which hold practical significance for production practices. Finally, we validated the compatibility and complementarity of our findings with existing theories.

Nov 5, 202418 min

Ep 11CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes

🤗 Paper Upvotes: 5 | cs.CV Authors: Yang Liu, Chuanchen Luo, Zhongkai Mao, Junran Peng, Zhaoxiang Zhang Title: CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes Arxiv: http://arxiv.org/abs/2411.00771v1 Abstract: Recently, 3D Gaussian Splatting (3DGS) has revolutionized radiance field reconstruction, manifesting efficient and high-fidelity novel view synthesis. However, accurately representing surfaces, especially in large and complex scenarios, remains a significant challenge due to the unstructured nature of 3DGS. In this paper, we present CityGaussianV2, a novel approach for large-scale scene reconstruction that addresses critical challenges related to geometric accuracy and efficiency. Building on the favorable generalization capabilities of 2D Gaussian Splatting (2DGS), we address its convergence and scalability issues. Specifically, we implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence. To scale up, we introduce an elongation filter that mitigates Gaussian count explosion caused by 2DGS degeneration. Furthermore, we optimize the CityGaussian pipeline for parallel training, achieving up to 10$\times$ compression, at least 25% savings in training time, and a 50% decrease in memory usage. We also established standard geometry benchmarks under large-scale scenes. Experimental results demonstrate that our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs. The project page is available at https://dekuliutesla.github.io/CityGaussianV2/.

Nov 5, 202420 min

Ep 10Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders

🤗 Daily Paper Upvotes: 57Authors: Viacheslav Surkov, Chris Wendler, Mikhail Terekhov, Justin Deschenaux, Robert West, Caglar GulcehreCategories: cs.LG, cs.AI, cs.CVArxiv: http://arxiv.org/abs/2410.22366v1Title: Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders Abstract: Sparse autoencoders (SAEs) have become a core ingredient in the reverse engineering of large-language models (LLMs). For LLMs, they have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and subsequent analysis. However, similar analyses and approaches have been lacking for text-to-image models. We investigated the possibility of using SAEs to learn interpretable features for a few-step text-to-image diffusion models, such as SDXL Turbo. To this end, we train SAEs on the updates performed by transformer blocks within SDXL Turbo's denoising U-net. We find that their learned features are interpretable, causally influence the generation process, and reveal specialization among the blocks. In particular, we find one block that deals mainly with image composition, one that is mainly responsible for adding local details, and one for color, illumination, and style. Therefore, our work is an important first step towards better understanding the internals of generative text-to-image models like SDXL Turbo and showcases the potential of features learned by SAEs for the visual domain. Code is available at https://github.com/surkovv/sdxl-unbox

Nov 3, 202423 min

Ep 9What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective

🤗 Daily Paper Upvotes: 45 Authors: Ming Li, Yanhong Li, Tianyi Zhou Categories: cs.CL, cs.AI, cs.LG Arxiv: http://arxiv.org/abs/2410.23743v1 Title: What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective Abstract: What makes a difference in the post-training of LLMs? We investigate the training patterns of different layers in large language models (LLMs), through the lens of gradient, when training with different responses and initial models. We are specifically interested in how fast vs. slow thinking affects the layer-wise gradients, given the recent popularity of training LLMs on reasoning paths such as chain-of-thoughts (CoT) and process rewards. In our study, fast thinking without CoT leads to larger gradients and larger differences of gradients across layers than slow thinking (Detailed CoT), indicating the learning stability brought by the latter. Moreover, pre-trained LLMs are less affected by the instability of fast thinking than instruction-tuned LLMs. Additionally, we study whether the gradient patterns can reflect the correctness of responses when training different LLMs using slow vs. fast thinking paths. The results show that the gradients of slow thinking can distinguish correct and irrelevant reasoning paths. As a comparison, we conduct similar gradient analyses on non-reasoning knowledge learning tasks, on which, however, trivially increasing the response length does not lead to similar behaviors of slow thinking. Our study strengthens fundamental understandings of LLM training and sheds novel insights on its efficiency and stability, which pave the way towards building a generalizable System-2 agent. Our code, data, and gradient statistics can be found in: https://github.com/MingLiiii/Layer_Gradient.

Nov 3, 202420 min

Ep 8A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents

🤗 Daily Paper Upvotes: 20 Authors: Ankan Mullick, Sombit Bose, Abhilash Nandy, Gajula Sai Chaitanya, Pawan Goyal Categories: cs.CL, cs.IR Arxiv: http://arxiv.org/abs/2410.22476v1 Title: A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents Abstract: In task-oriented dialogue systems, intent detection is crucial for interpreting user queries and providing appropriate responses. Existing research primarily addresses simple queries with a single intent, lacking effective systems for handling complex queries with multiple intents and extracting different intent spans. Additionally, there is a notable absence of multilingual, multi-intent datasets. This study addresses three critical tasks: extracting multiple intent spans from queries, detecting multiple intents, and developing a multi-lingual multi-label intent dataset. We introduce a novel multi-label multi-class intent detection dataset (MLMCID-dataset) curated from existing benchmark datasets. We also propose a pointer network-based architecture (MLMCID) to extract intent spans and detect multiple intents with coarse and fine-grained labels in the form of sextuplets. Comprehensive analysis demonstrates the superiority of our pointer network-based system over baseline approaches in terms of accuracy and F1-score across various datasets.

Nov 3, 202422 min

Ep 7Language Models can Self-Lengthen to Generate Long Texts

🤗 Daily Paper Upvotes: 14 Authors: Shanghaoran Quan, Tianyi Tang, Bowen Yu, An Yang, Dayiheng Liu, Bofei Gao, Jianhong Tu, Yichang Zhang, Jingren Zhou, Junyang Lin Categories: cs.CL Arxiv: http://arxiv.org/abs/2410.23933v1 Title: Language Models can Self-Lengthen to Generate Long Texts Abstract: Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating long, aligned outputs. This limitation stems from a training gap where pre-training lacks effective instructions for long-text generation, and post-training data primarily consists of short query-response pairs. Current approaches, such as instruction backtranslation and behavior imitation, face challenges including data quality, copyright issues, and constraints on proprietary model usage. In this paper, we introduce an innovative iterative training framework called Self-Lengthen that leverages only the intrinsic knowledge and skills of LLMs without the need for auxiliary data or proprietary models. The framework consists of two roles: the Generator and the Extender. The Generator produces the initial response, which is then split and expanded by the Extender. This process results in a new, longer response, which is used to train both the Generator and the Extender iteratively. Through this process, the models are progressively trained to handle increasingly longer responses. Experiments on benchmarks and human evaluations show that Self-Lengthen outperforms existing methods in long-text generation, when applied to top open-source LLMs such as Qwen2 and LLaMA3. Our code is publicly available at https://github.com/QwenLM/Self-Lengthen.

Nov 3, 202420 min

Ep 6Constraint Back-translation Improves Complex Instruction Following of Large Language Models

🤗 Daily Paper Upvotes: 12 Authors: Yunjia Qi, Hao Peng, Xiaozhi Wang, Bin Xu, Lei Hou, Juanzi Li Categories: cs.CL, cs.AI Arxiv: http://arxiv.org/abs/2410.24175v1 Title: Constraint Back-translation Improves Complex Instruction Following of Large Language Models Abstract: Large language models (LLMs) struggle to follow instructions with complex constraints in format, length, etc. Following the conventional instruction-tuning practice, previous works conduct post-training on complex instruction-response pairs generated by feeding complex instructions to advanced LLMs. However, even advanced LLMs cannot follow complex instructions well, thus limiting the quality of generated data. In this work, we find that existing datasets inherently contain implicit complex constraints and propose a novel data generation technique, constraint back-translation. Specifically, we take the high-quality instruction-response pairs in existing datasets and only adopt advanced LLMs to add complex constraints already met by the responses to the instructions, which naturally reduces costs and data noise. In the experiments, we adopt Llama3-70B-Instruct to back-translate constraints and create a high-quality complex instruction-response dataset, named CRAB. We present that post-training on CRAB improves multiple backbone LLMs' complex instruction-following ability, evaluated on extensive instruction-following benchmarks. We further find that constraint back-translation also serves as a useful auxiliary training objective in post-training. Our code, data, and models will be released to facilitate future research.

Nov 3, 202419 min

Ep 5BitStack: Fine-Grained Size Control for Compressed Large Language Models in Variable Memory Environments

🤗 Daily Paper Upvotes: 11 Authors: Xinghao Wang, Pengyu Wang, Bo Wang, Dong Zhang, Yunhua Zhou, Xipeng Qiu Categories: cs.CL, cs.AI, cs.CV, cs.LG Arxiv: http://arxiv.org/abs/2410.23918v1 Title: BitStack: Fine-Grained Size Control for Compressed Large Language Models in Variable Memory Environments Abstract: Large language models (LLMs) have revolutionized numerous applications, yet their deployment remains challenged by memory constraints on local devices. While scaling laws have enhanced LLM capabilities, the primary bottleneck has shifted from \textit{capability} to \textit{availability}, emphasizing the need for efficient memory management. Traditional compression methods, such as quantization, often require predefined compression ratios and separate compression processes for each setting, complicating deployment in variable memory environments. In this paper, we introduce \textbf{BitStack}, a novel, training-free weight compression approach that enables megabyte-level trade-offs between memory usage and model performance. By leveraging weight decomposition, BitStack can dynamically adjust the model size with minimal transmission between running memory and storage devices. Our approach iteratively decomposes weight matrices while considering the significance of each parameter, resulting in an approximately 1-bit per parameter residual block in each decomposition iteration. These blocks are sorted and stacked in storage as basic transmission units, with different quantities loaded based on current memory availability. Extensive experiments across a wide range of tasks demonstrate that, despite offering fine-grained size control, BitStack consistently matches or surpasses strong quantization baselines, particularly at extreme compression ratios. To the best of our knowledge, this is the first decomposition-based method that effectively bridges the gap to practical compression techniques like quantization. Code is available at https://github.com/xinghaow99/BitStack.

Nov 3, 202417 min

Ep 4SelfCodeAlign: Self-Alignment for Code Generation

🤗 Daily Paper Upvotes: 11 Authors: Yuxiang Wei, Federico Cassano, Jiawei Liu, Yifeng Ding, Naman Jain, Zachary Mueller, Harm de Vries, Leandro von Werra, Arjun Guha, Lingming Zhang Categories: cs.CL, cs.LG, cs.SE Arxiv: http://arxiv.org/abs/2410.24198v1 Title: SelfCodeAlign: Self-Alignment for Code Generation Abstract: Instruction tuning is a supervised fine-tuning approach that significantly improves the ability of large language models (LLMs) to follow human instructions. We propose SelfCodeAlign, the first fully transparent and permissive pipeline for self-aligning code LLMs without extensive human annotations or distillation. SelfCodeAlign employs the same base model for inference throughout the data generation process. It first extracts diverse coding concepts from high-quality seed snippets to generate new tasks. It then samples multiple responses per task, pairs each with test cases, and validates them in a sandbox environment. Finally, passing examples are selected for instruction tuning. In our primary experiments, we use SelfCodeAlign with CodeQwen1.5-7B to generate a dataset of 74k instruction-response pairs. Finetuning on this dataset leads to a model that achieves a 67.1 pass@1 on HumanEval+, surpassing CodeLlama-70B-Instruct despite being ten times smaller. Across all benchmarks, this finetuned model consistently outperforms the original version trained with OctoPack, the previous state-of-the-art method for instruction tuning without human annotations or distillation. Additionally, we show that SelfCodeAlign is effective across LLMs of various sizes, from 3B to 33B, and that the base models can benefit more from alignment with their own data distribution. We further validate each component's effectiveness in our pipeline, showing that SelfCodeAlign outperforms both direct distillation from GPT-4o and leading GPT-3.5-based distillation methods, such as OSS-Instruct and Evol-Instruct. SelfCodeAlign has also led to the creation of StarCoder2-Instruct, the first fully transparent, permissively licensed, and self-aligned code LLM that achieves state-of-the-art coding performance.

Nov 3, 202418 min

Ep 3Learning Video Representations without Natural Videos

🤗 Daily Paper Upvotes: 10 Authors: Xueyang Yu, Xinlei Chen, Yossi Gandelsman Categories: cs.CV Arxiv: http://arxiv.org/abs/2410.24213v1 Title: Learning Video Representations without Natural Videos Abstract: In this paper, we show that useful video representations can be learned from synthetic videos and natural images, without incorporating natural videos in the training. We propose a progression of video datasets synthesized by simple generative processes, that model a growing set of natural video properties (e.g. motion, acceleration, and shape transformations). The downstream performance of video models pre-trained on these generated datasets gradually increases with the dataset progression. A VideoMAE model pre-trained on our synthetic videos closes 97.2% of the performance gap on UCF101 action classification between training from scratch and self-supervised pre-training from natural videos, and outperforms the pre-trained model on HMDB51. Introducing crops of static images to the pre-training stage results in similar performance to UCF101 pre-training and outperforms the UCF101 pre-trained model on 11 out of 14 out-of-distribution datasets of UCF101-P. Analyzing the low-level properties of the datasets, we identify correlations between frame diversity, frame similarity to natural data, and downstream performance. Our approach provides a more controllable and transparent alternative to video data curation processes for pre-training.

Nov 3, 202422 min

Ep 2AAAR-1.0: Assessing AI's Potential to Assist Research

🤗 Daily Paper Upvotes: 10 Authors: Renze Lou, Hanzi Xu, Sijia Wang, Jiangshu Du, Ryo Kamoi, Xiaoxin Lu, Jian Xie, Yuxuan Sun, Yusen Zhang, Jihyun Janice Ahn, Hongchao Fang, Zhuoyang Zou, Wenchao Ma, Xi Li, Kai Zhang, Congying Xia, Lifu Huang, Wenpeng Yin Categories: cs.CL Arxiv: http://arxiv.org/abs/2410.22394v1 Title: AAAR-1.0: Assessing AI's Potential to Assist Research Abstract: Numerous studies have assessed the proficiency of AI systems, particularly large language models (LLMs), in facilitating everyday tasks such as email writing, question answering, and creative content generation. However, researchers face unique challenges and opportunities in leveraging LLMs for their own work, such as brainstorming research ideas, designing experiments, and writing or reviewing papers. In this study, we introduce AAAR-1.0, a benchmark dataset designed to evaluate LLM performance in three fundamental, expertise-intensive research tasks: (i) EquationInference, assessing the correctness of equations based on the contextual information in paper submissions; (ii) ExperimentDesign, designing experiments to validate research ideas and solutions; (iii) PaperWeakness, identifying weaknesses in paper submissions; and (iv) REVIEWCRITIQUE, identifying each segment in human reviews is deficient or not. AAAR-1.0 differs from prior benchmarks in two key ways: first, it is explicitly research-oriented, with tasks requiring deep domain expertise; second, it is researcher-oriented, mirroring the primary activities that researchers engage in on a daily basis. An evaluation of both open-source and proprietary LLMs reveals their potential as well as limitations in conducting sophisticated research tasks. We will keep iterating AAAR-1.0 to new versions.

Nov 3, 202422 min

Ep 1BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays

🤗 Daily Paper Upvotes: 7 Authors: Yang Zhou, Tan Li Hui Faith, Yanyu Xu, Sicong Leng, Xinxing Xu, Yong Liu, Rick Siow Mong Goh Categories: cs.CV Arxiv: http://arxiv.org/abs/2410.21969v1 Title: BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays Abstract: Medical Vision-Language Pretraining (MedVLP) shows promise in learning generalizable and transferable visual representations from paired and unpaired medical images and reports. MedVLP can provide useful features to downstream tasks and facilitate adapting task-specific models to new setups using fewer examples. However, existing MedVLP methods often differ in terms of datasets, preprocessing, and finetuning implementations. This pose great challenges in evaluating how well a MedVLP method generalizes to various clinically-relevant tasks due to the lack of unified, standardized, and comprehensive benchmark. To fill this gap, we propose BenchX, a unified benchmark framework that enables head-to-head comparison and systematical analysis between MedVLP methods using public chest X-ray datasets. Specifically, BenchX is composed of three components: 1) Comprehensive datasets covering nine datasets and four medical tasks; 2) Benchmark suites to standardize data preprocessing, train-test splits, and parameter selection; 3) Unified finetuning protocols that accommodate heterogeneous MedVLP methods for consistent task adaptation in classification, segmentation, and report generation, respectively. Utilizing BenchX, we establish baselines for nine state-of-the-art MedVLP methods and found that the performance of some early MedVLP methods can be enhanced to surpass more recent ones, prompting a revisiting of the developments and conclusions from prior works in MedVLP. Our code are available at https://github.com/yangzhou12/BenchX.

Nov 3, 202421 min