The AgentSociety Challenge is the first competition in the Web Conference that aims to explore the potential of Large Language Model (LLM) agents in modeling user behavior and enhancing recommender systems on web platforms. The Challenge consists of two tracks: the User Modeling Track and the Recommendation Track. Participants are tasked to utilize a combined dataset from Yelp, Amazon, and Goodreads, along with an interactive environment simulator, to develop innovative LLM agents. The Challenge has attracted 295 teams across the globe and received over 1,400 submissions in total over the course of 37 official competition days. The participants have achieved 21.9% and 20.3% performance improvement for Track 1 and Track 2 in the Development Phase, and 9.1% and 15.9% in the Final Phase, representing a significant accomplishment. This paper discusses the detailed designs of the Challenge, analyzes the outcomes, and highlights the most successful LLM agent designs. To support further research and development, we have open-sourced the benchmark environment at https://tsinghua-fib-lab.github.io/AgentSocietyChallenge.

Stable Diffusion has achieved remarkable success in the field of text-to-image generation, with its powerful generative capabilities and diverse generation results making a lasting impact. However, its iterative denoising introduces high computational costs and slows generation speed, limiting broader adoption. The community has made numerous efforts to reduce this computational burden, with methods like feature caching attracting attention due to their effectiveness and simplicity. Nonetheless, simply reusing features computed at previous timesteps causes the features across adjacent timesteps to become similar, reducing the dynamics of features over time and ultimately compromising the quality of generated images. In this paper, we introduce a dynamics-aware token pruning (DaTo) approach that addresses the limitations of feature caching. DaTo selectively prunes tokens with lower dynamics, allowing only high-dynamic tokens to participate in self-attention layers, thereby extending feature dynamics across timesteps. DaTo combines feature caching with token pruning in a training-free manner, achieving both temporal and token-wise information reuse. Applied to Stable Diffusion on the ImageNet, our approach delivered a 9$\times$ speedup while reducing FID by 0.33, indicating enhanced image quality. On the COCO-30k, we observed a 7$\times$ acceleration coupled with a notable FID reduction of 2.17.

The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing token reduction methods primarily focus on importance-based token pruning, which overlooks the redundancy caused by frame resemblance and repetitive visual elements. In this paper, we analyze the high vision token similarities in LVLMs. We reveal that token similarity distribution condenses as layers deepen while maintaining ranking consistency. Leveraging the unique properties of similarity over importance, we introduce FrameFusion, a novel approach that combines similarity-based merging with importance-based pruning for better token reduction in LVLMs. FrameFusion identifies and merges similar tokens before pruning, opening up a new perspective for token reduction. We evaluate FrameFusion on diverse LVLMs, including Llava-Video-{7B,32B,72B}, and MiniCPM-V-8B, on video understanding, question-answering, and retrieval benchmarks. Experiments show that FrameFusion reduces vision tokens by 70$\%$, achieving 3.4-4.4x LLM speedups and 1.6-1.9x end-to-end speedups, with an average performance impact of less than 3$\%$. Our code is available at https://github.com/thu-nics/FrameFusion.

Vision-Language Models (VLMs) have enabled a variety of real-world applications. The large parameter size of VLMs brings large memory and computation overhead which poses significant challenges for deployment. Post-Training Quantization (PTQ) is an effective technique to reduce the memory and computation overhead. Existing PTQ methods mainly focus on large language models (LLMs), without considering the differences across other modalities. In this paper, we discover that there is a significant difference in sensitivity between language and vision tokens in large VLMs. Therefore, treating tokens from different modalities equally, as in existing PTQ methods, may over-emphasize the insensitive modalities, leading to significant accuracy loss. To deal with the above issue, we propose a simple yet effective method, Modality-Balanced Quantization (MBQ), for large VLMs. Specifically, MBQ incorporates the different sensitivities across modalities during the calibration process to minimize the reconstruction loss for better quantization parameters. Extensive experiments show that MBQ can significantly improve task accuracy by up to 4.4% and 11.6% under W3 and W4A8 quantization for 7B to 70B VLMs, compared to SOTA baselines. Additionally, we implement a W3 GPU kernel that fuses the dequantization and GEMV operators, achieving a 1.4x speedup on LLaVA-onevision-7B on the RTX 4090. The code is available at https://github.com/thu-nics/MBQ.

Autoregressive (AR) models have recently achieved state-of-the-art performance in text and image generation. However, their primary limitation is slow generation speed due to the token-by-token process. We ask an ambitious question: can a pre-trained AR model be adapted to generate outputs in just one or two steps? If successful, this would significantly advance the development and deployment of AR models. We notice that existing works that attempt to speed up AR generation by generating multiple tokens at once fundamentally cannot capture the output distribution due to the conditional dependencies between tokens, limiting their effectiveness for few-step generation. To overcome this, we propose Distilled Decoding (DD), which leverages flow matching to create a deterministic mapping from Gaussian distribution to the output distribution of the pre-trained AR model. We then train a network to distill this mapping, enabling few-step generation. The entire training process of DD does not need the training data of the original AR model (as opposed to some other methods), thus making DD more practical. We evaluate DD on state-of-the-art image AR models and present promising results. For VAR, which requires 10-step generation (680 tokens), DD enables onestep generation (6.3 speed-up), with an acceptable increase in FID from 4.19 to 9.96 on ImageNet-256. Similarly, for LlamaGen, DD reduces generation from 256 steps to 1, achieving an 217.8 speed-up with a comparable FID increase from 4.11 to 11.35 on ImageNet-256. In both cases, baseline methods completely fail with FID scores >100. As the first work to demonstrate the possibility of onestep generation for image AR models, DD challenges the prevailing notion that AR models are inherently slow, and opens up new opportunities for efficient AR generation.

Neural network training is a memory-and compute-intensive task. Quantization, which enables low-bitwidth formats in training, can significantly mitigate the workload. To reduce quantization error, recent methods have developed new data formats and additional pre-processing operations on quantizers. However, it remains quite challenging to achieve high accuracy and efficiency simultaneously. In this paper, we explore sub-8-bit integer training from its essence of gradient descent optimization. Our integer training framework includes two components: ShiftQuant to realize accurate gradient estimation, and L1 normalization to smoothen the loss landscape. ShiftQuant attains performance that approaches the theoretical upper bound of group quantization. Our method frees sub-8-bit integer training from pre-processing and supports general devices. This framework achieves negligible accuracy loss across various neural networks and tasks (0.92% on 4-bit ResNets, 0.61% on 6-bit Transformers). The prototypical implementation of ShiftQuant achieves more than 1.85 /15.3% performance improvement on CPU/GPU compared to its FP16 counterparts, and 33.9% resource consumption reduction on FPGA than the FP16 counterparts. The proposed fully-quantized L1 normalization layers achieve more than 35.54% improvement in throughout on CPU compared to traditional L2 normalization layers.

Diffusion models are trained by learning a sequence of models that reverse each step of noise corruption. Typically, the model parameters are fully shared across multiple timesteps to enhance training efficiency. However, since the denoising tasks differ at each timestep, the gradients computed at different timesteps may conflict, potentially degrading the overall performance of image generation. To solve this issue, this work proposes a Decouple-then-Merge (DeMe) framework, which begins with a pretrained model and finetunes separate models tailored to specific timesteps. We introduce several improved techniques during the finetuning stage to promote effective knowledge sharing while minimizing training interference across timesteps. Finally, after finetuning, these separate models can be merged into a single model in the parameter space, ensuring efficient and practical inference. Experimental results show significant generation quality improvements upon 6 benchmarks including Stable Diffusion on COCO30K, ImageNet1K, PartiPrompts, and DDPM on LSUN Church, LSUN Bedroom, and CIFAR10. Generative modeling has seen significant progress in recent years, primarily driven by the development of Diffusion Probabilistic Models (DPMs) (Ho et al., 2020; Nichol & Dhariwal, 2021; Rombach et al., 2022b). These models have been applied to various tasks such as text-to-image generation (Rombach et al., 2022a), image-to-image translation (Saharia et al., 2022a), image editing (Yang et al., 2023a), and video generation (Ho et al., 2022; Blattmann et al., 2023), yielding excellent performance. Compared with other generative models such as variational auto-encoders (VAEs) (Kingma & Welling, 2013), and generative adversarial networks (GANs) (Goodfellow et al., 2014), the most distinct characteristic of DPMs is that DPMs need to learn a sequence of models for denoising at multiple timesteps.

Sparse attention can effectively mitigate the significant memory and throughput demands of Large Language Models (LLMs) in long contexts. Existing methods typically employ a uniform sparse attention mask, applying the same sparse pattern across different attention heads and input lengths. However, this uniform approach fails to capture the diverse attention patterns inherent in LLMs, ignoring their distinct accuracy-latency trade-offs. To address this challenge, we propose the Mixture of Attention (MoA), which automatically tailors distinct sparse attention configurations to different heads and layers. MoA constructs and navigates a search space of various attention patterns and their scaling rules relative to input sequence lengths. It profiles the model, evaluates potential configurations, and pinpoints the optimal sparse attention compression plan. MoA adapts to varying input sizes, revealing that some attention heads expand their focus to accommodate longer sequences, while other heads consistently concentrate on fixed-length local contexts. Experiments show that MoA increases the effective context length by $3.9\times$ with the same average attention span, boosting retrieval accuracy by $1.5-7.1\times$ over the uniform-attention baseline across Vicuna-7B, Vicuna-13B, and Llama3-8B models. Moreover, MoA narrows the capability gaps between sparse and dense models, reducing the maximum relative performance drop from $9\%-36\%$ to within $5\%$ across two long-context understanding benchmarks. MoA achieves a $1.2-1.4\times$ GPU memory reduction and boosts decode throughput by $5.5-6.7 \times$ for 7B and 13B dense models on a single GPU, with minimal impact on performance.

Teaching to improve student models (e.g., knowledge distillation) is an extensively studied methodology in LLMs. However, for humans, teaching not only improves students but also improves teachers. We ask: Can LLMs also learn by teaching (LbT)? If yes, we can potentially unlock the possibility of continuously advancing the models without solely relying on human-produced data or stronger models. In this paper, we provide a preliminary exploration of this ambitious agenda. We show that LbT ideas can be incorporated into existing LLM training/prompting pipelines and provide noticeable improvements. Specifically, we design three methods, each mimicking one of the three levels of LbT in humans: observing students' feedback, learning from the feedback, and learning iteratively, with the goals of improving answer accuracy without training and improving models' inherent capability with fine-tuning. The findings are encouraging. For example, similar to LbT in human, we see that: (1) LbT can induce weak-to-strong generalization: strong models can improve themselves by teaching other weak models; (2) Diversity in students might help: teaching multiple students could be better than teaching one student or the teacher itself. We hope that this early promise can inspire future research on LbT and more broadly adopting the advanced techniques in education to improve LLMs. The code is available at https://github.com/imagination-research/lbt.

Large Language Models (LLMs) have attracted extensive attention due to their remarkable performance across various tasks. However, the substantial computational and memory requirements of LLM inference pose challenges for deployment in resource-constrained scenarios. Efforts within the field have been directed towards developing techniques aimed at enhancing the efficiency of LLM inference. This paper presents a comprehensive survey of the existing literature on efficient LLM inference. We start by analyzing the primary causes of the inefficient LLM inference, i.e., the large model size, the quadratic-complexity attention operation, and the auto-regressive decoding approach. Then, we introduce a comprehensive taxonomy that organizes the current literature into data-level, model-level, and system-level optimization. Moreover, the paper includes comparative experiments on representative methods within critical sub-fields to provide quantitative insights. Last but not least, we provide some knowledge summary and discuss future research directions.