Related papers: M2R2: Mixture of Multi-Rate Residuals for Efficien…

High-resolution Multimodal Large Language Models (MLLMs) face prohibitive computational costs during inference due to the explosion of visual tokens. Existing acceleration strategies, such as token pruning or layer sparsity, suffer from…

Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision. Most existing multimodal explainable AI (MXAI) methods extend unimodal saliency to multimodal backbones, highlighting…

Autoregressive decoding in large language models (LLMs) requires $\mathcal{O}(n)$ sequential steps for $n$ tokens, fundamentally limiting inference throughput. Recent diffusion-based LLMs (dLLMs) enable parallel token generation through…

The vanilla self-attention mechanism in Transformers can be viewed as a two-layer fast-weight MLP, whose weights are dynamically induced by inputs and whose hidden dimension is equal to the sequence length $N$. As the context extends, the…

Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally…

Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…

The introduction of the neural implicit representation has notably propelled the advancement of online dense reconstruction techniques. Compared to traditional explicit representations, such as TSDF, it improves the mapping completeness and…

Large Language Models (LLMs) with Mixture-of-Experts (MoE) architectures are distinguished by their strong performance scaling with increasing parameters across a wide range of tasks, yet they also suffer from substantial computational and…

Sparse Mixture of Experts (MoE) large language models (LLMs) are gradually becoming the mainstream approach for ultra-large-scale models. Existing optimization efforts for MoE models have focused primarily on coarse-grained MoE…

This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model's…

Achieving self-evolution in intelligent agents requires the continual accumulation of new knowledge across changing task sequences without forgetting previously acquired abilities. Existing approaches either internalize knowledge by…

Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often rely heavily on…

With the rapid advancement of multimodal retrieval and its application in LLMs and multimodal LLMs, increasingly complex retrieval tasks have emerged. Existing methods predominantly rely on task-specific fine-tuning of vision-language…

Mixture-of-Experts (MoE) large language models (LLM) have memory requirements that often exceed the GPU memory capacity, requiring costly parameter movement from secondary memories to the GPU for expert computation. In this work, we present…

While large language models (LLMs) excel on generation tasks, their decoder-only architecture often limits their potential as embedding models if no further representation finetuning is applied. Does this contradict their claim of…

Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge. However, existing work has three key limitations: (1) most efforts focus on…

The training of deep residual neural networks (ResNets) with backpropagation has a memory cost that increases linearly with respect to the depth of the network. A way to circumvent this issue is to use reversible architectures. In this…

Large Transformer models have achieved state-of-the-art results in neural machine translation and have become standard in the field. In this work, we look for the optimal combination of known techniques to optimize inference speed without…

We present the Mixture-of-Tunable-Experts (MoTE), a method that extends the Mixture-of-Experts architecture of Large Language Models (LLMs). Without additional training, MoTE enables meaningful and focused behavior changes in LLMs…

Current end-to-end spoken language models (SLMs) have made notable progress, yet they still encounter considerable response latency. This delay primarily arises from the autoregressive generation of speech tokens and the reliance on complex…