Related papers: Hydra: Unifying Document Retrieval and Generation …

Conventional document layout analysis (DLA) traditionally depends on empirical priors or a fixed set of learnable queries executed in a single forward pass. While sufficient for early-generation documents with a small, predetermined number…

Multimodal Large Language Models (MLLMs) have advanced unified reasoning over text, images, and videos, but their inference is hindered by the rapid growth of key-value (KV) caches. Each visual input expands into thousands of tokens,…

Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attention heads consumes substantial memory. Existing KV cache…

Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences. Existing routers make binary strong-vs-weak decisions and couple learned parameters to specific model identities,…

Motivated by the growing demand for retrieval systems that operate across modalities, we introduce llama-nemoretriever-colembed, a unified text-image retrieval model that delivers state-of-the-art performance across multiple benchmarks. We…

Parameter efficient fine tuning methods like LoRA have enabled task specific adaptation of large language models, but efficiently composing multiple specialized adapters for unseen tasks remains challenging. We present a novel framework for…

Retrieval-augmented generation (RAG) has become a dominant paradigm for mitigating knowledge hallucination and staleness in large language models (LLMs) while preserving data security. By retrieving relevant evidence from private,…

Large Language Models (LLMs) have demonstrated significant potential in medical Question Answering (QA), yet they remain prone to hallucinations and ungrounded reasoning, limiting their reliability in high-stakes clinical scenarios. While…

Vision-Language Model (VLM) based retrievers have advanced visual document retrieval (VDR) to impressive quality. They require the same multi-billion parameter encoder for both document indexing and query encoding, incurring high latency…

As deep learning becomes more expensive, both in terms of time and compute, inefficiencies in machine learning (ML) training prevent practical usage of state-of-the-art models for most users. The newest model architectures are simply too…

Low-rank adaptation (LoRA) is a predominant parameter-efficient finetuning method for adapting large language models (LLMs) to downstream tasks. Meanwhile, Compute-in-Memory (CIM) architectures demonstrate superior energy efficiency due to…

As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI. However, previous omni-models have insufficiently explored speech,…

Generative information retrieval, encompassing two major tasks of Generative Document Retrieval (GDR) and Grounded Answer Generation (GAR), has gained significant attention in the area of information retrieval and natural language…

We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared…

Distilling vision-language models into faster hybrid architectures, such as 3:1 Mamba-2/attention mixes, is now standard practice for making inference efficient. Aggregate benchmarks suggest that this works but they hide selective failures.…

Large Language Models (LLMs) excel in language comprehension and generation but are prone to hallucinations, producing factually incorrect or unsupported outputs. Retrieval Augmented Generation (RAG) systems address this issue by grounding…

While Vision-Language Models (VLMs) have shown promise in textual understanding, they face significant challenges when handling long context and complex reasoning tasks. In this paper, we dissect the internal mechanisms governing…

Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective memory in recurrent designs. We present LoGeR…

As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and computational bottlenecks during inference. While Multi-Head Latent Attention (MLA)…

Large language model (LLM) agents demonstrate strong performance in short-text contexts but often underperform in extended dialogues due to inefficient memory management. Existing approaches face a fundamental trade-off between efficiency…