Related papers: Semantic Trimming and Auxiliary Multi-step Predict…

Modern recommender systems perform large-scale retrieval by first embedding queries and item candidates in the same unified space, followed by approximate nearest neighbor search to select top candidates given a query embedding. In this…

We introduce TriAlignGR, a unified multitask-multimodal framework for generative recommendation that establishes two-stage multimodal semantic propagation: (i) encoding visual semantics directly into SIDs via multimodal embeddings, and (ii)…

Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing approaches typically address this issue using single-layer Vision Transformer (ViT)…

Recent studies have demonstrated that many layers are functionally redundant in large language models (LLMs), enabling model compression by removing these layers to reduce inference cost. While such approaches can improve efficiency,…

Obtaining human per-pixel labels for semantic segmentation is incredibly laborious, often making labeled dataset construction prohibitively expensive. Here, we endeavor to overcome this problem with a novel algorithm that combines…

The deployment of large language models (LLMs) is often constrained by their substantial computational and memory demands. While structured pruning presents a viable approach by eliminating entire network components, existing methods suffer…

Multi-label learning is a challenging computer vision task that requires assigning multiple categories to each image. However, fully annotating large-scale datasets is often impractical due to high costs and effort, motivating the study of…

Large language model (LLM)-based generative list-wise recommendation has advanced rapidly, but decoding remains sequential and thus latency-prone. To accelerate inference without changing the target distribution, speculative decoding (SD)…

Sequential recommendations (SR) predict users' future interactions based on their historical behavior. The rise of Large Language Models (LLMs) has brought powerful generative and reasoning capabilities, significantly enhancing SR…

Spike-timing-dependent-plasticity (STDP) is an unsupervised learning algorithm for spiking neural network (SNN), which promises to achieve deeper understanding of human brain and more powerful artificial intelligence. While conventional…

Due to the binary spike signals making converting the traditional high-power multiply-accumulation (MAC) into a low-power accumulation (AC) available, the brain-inspired Spiking Neural Networks (SNNs) are gaining more and more attention.…

Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training sample. However, this approach can be inefficient and yield…

Repeated Sampling (RS) is a simple inference-time algorithm that has been shown to improve model performance on complex tasks. Although it is an effective way of scaling inference time, it often struggles to generate diverse solution…

Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variety of domains. However, training MLLMs is often inefficient, as much of the computation is redundant due to the long input sequences from…

Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead…

We present a novel sparsity-based space-time adaptive processing (STAP) technique based on the alternating direction method to overcome the severe performance degradation caused by array gain/phase (GP) errors. The proposed algorithm…

Space-time adaptive processing (STAP) algorithms with coprime arrays can provide good clutter suppression potential with low cost in airborne radar systems as compared with their uniform linear arrays counterparts. However, the performance…

Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains…

Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and skipping, have shown great promise in reducing inference…

Despite the recent success of large language models (LLMs), LLMs are particularly challenging in long-sequence inference scenarios due to the quadratic computational complexity of the attention mechanism. Inspired by the interpretability…