Related papers: Screening Is Enough
The rapid proliferation of LLMs has created a critical evaluation paradox: while LLMs claim multilingual proficiency, comprehensive non-machine-translated benchmarks exist for fewer than 30 languages, leaving >98% of the world's 7,000…
The ability to decompose complex natural scenes into meaningful object-centric abstractions lies at the core of human perception and reasoning. In the recent culmination of unsupervised object-centric learning, the Slot-Attention module has…
The transformer architecture is central to the success of modern Large Language Models (LLMs), in part due to its surprising ability to perform a wide range of tasks - including mathematical reasoning, memorization, and retrieval - using…
Transformer-based architectures traditionally employ softmax to compute attention weights, which produces dense distributions over all tokens in a sequence. While effective in many settings, this density has been shown to be detrimental for…
KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from…
Long video understanding remains a formidable challenge for Multimodal Large Language Models (MLLMs) due to the prohibitive computational cost of processing dense frame sequences. Prevailing solutions, which select a keyframe subset,…
Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…
Learning systems match predicted scores to observations over some domain. Often, it is critical to produce accurate predictions in some subset (or region) of the domain, yet less important to accurately predict in other regions. We…
Referring Expression Comprehension (REC) requires models to localize objects in images based on natural language descriptions. Research on the area remains predominantly English-centric, despite increasing global deployment demands. This…
Standard attention scales quadratically with sequence length. Efficient attention methods reduce this O(n^2) cost, but when retrofitted into pretrained models, they often degrade perplexity, downstream accuracy, or both. We introduce Focus,…
Large multimodal models (LMMs) have recently demonstrated remarkable performance in video question answering (VideoQA), yet reasoning over video remains challenging due to high inference cost and diluted information. Keyframe selection…
Soft attention in Transformer-based Large Language Models (LLMs) is susceptible to incorporating irrelevant information from the context into its latent representations, which adversely affects next token generations. To help rectify these…
Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max…
Large language models have achieved remarkable success in recent years, primarily due to self-attention. However, traditional Softmax attention suffers from numerical instability and reduced performance as the number of inference tokens…
The self-attention mechanism traditionally relies on the softmax operator, necessitating positional embeddings like RoPE, or position biases to account for token order. But current methods using still face length generalisation challenges.…
The attention module is the key component in Transformers. While the global attention mechanism offers high expressiveness, its excessive computational cost restricts its applicability in various scenarios. In this paper, we propose a novel…
Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts. Sparse attention methods offer a promising solution, but existing approaches often suffer…
Question retrieval is a crucial subtask for community question answering. Previous research focus on supervised models which depend heavily on training data and manual feature engineering. In this paper, we propose a novel unsupervised…
Attention mechanisms represent a fundamental paradigm shift in neural network architectures, enabling models to selectively focus on relevant portions of input sequences through learned weighting functions. This monograph provides a…
We introduce a new architecture for unsupervised object-centric representation learning and multi-object detection and segmentation, which uses a translation-equivariant attention mechanism to predict the coordinates of the objects present…