相关论文: CLAA: Cross-Layer Attention Aggregation for Accele…

The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (SSMs) provide scalable alternatives but are typically…

Large Language Models (LLMs) show promising results in language generation and instruction following but frequently "hallucinate", making their outputs less reliable. Despite Uncertainty Quantification's (UQ) potential solutions,…

Large Language Models (LLMs) rely on the Key-Value (KV) Cache to store token history, enabling efficient decoding of tokens. As the KV-Cache grows, it becomes a major memory and computation bottleneck. However, there is an opportunity to…

Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent…

Providing external knowledge to Large Language Models (LLMs) is a key point for using these models in real-world applications for several reasons, such as incorporating up-to-date content in a real-time manner, providing access to…

Large Language Models (LLMs) have significantly advanced the field of Artificial Intelligence. However, their deployment is resource-intensive, not only due to the large number of model parameters but also because the (Key-Value) KV cache…

Large Language Models (LLMs), despite their success in question answering, exhibit limitations in complex multi-hop question answering (MQA) tasks that necessitate non-linear, structured reasoning. This limitation stems from their inability…

Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is expensive due to the quadratic scaling of Attention. We…

Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computational load and…

Advances in Generative AI have made video-level deepfake detection increasingly challenging, exposing the limitations of current detection techniques. In this paper, we present HOLA, our solution to the Video-Level Deepfake Detection track…

Memory and computation remain core bottlenecks in long-horizon LLM inference due to the quadratic cost of self-attention and the ever-growing key-value (KV) cache. Existing strategies for memory-bounded inference, such as quantization,…

Column Type Annotation (CTA) is a fundamental step towards enabling schema alignment and semantic understanding of tabular data. Existing encoder-only language models achieve high accuracy when fine-tuned on labeled columns, but their…

Multi-Head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value states into a low-rank latent vector, caching only this vector to reduce memory. In tensor parallelism (TP), however, attention heads are computed across…

Token-level adaptive computation seeks to reduce inference cost by allocating more computation to harder tokens and less to easier ones. However, prior work is primarily evaluated on natural-language benchmarks using task-level metrics,…

Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration strategy, applying it at shallow decoder layers often causes…

Table images present unique challenges for effective and efficient understanding due to the need for question-specific focus and the presence of redundant background regions. Existing Multimodal Large Language Model (MLLM) approaches often…

The pervasive deployment of large language models (LLMs) in conversational AI systems has revolutionized information access, yet their propensity for generating factually unsupported or hallucinated responses remains a critical impediment…

Large language models (LLMs) exhibit strong reasoning capabilities but typically require expensive post-training to reach high performance. Recent test-time alignment methods offer a lightweight alternative, but have been explored mainly…

This paper proposes Block-Filtered Long-Context Attention (BFLA), a training-free sparse prefill attention mechanism for long-context inference. BFLA adopts a two-stage design. In Stage 1, query and key sequences are compressed into coarse…

Large Language Models (LLMs) exhibit high inference latency due to their autoregressive decoding nature. While the draft head in speculative decoding mitigates this issue, its full potential remains unexplored. In this paper, we introduce…