Related papers: PAFFA: Premeditated Actions For Fast Agents

When generating outputs for domains with specific validity constraints (e.g., a program should compile), LLMs often fail in a small number of focused ways: for example, by using Python function names when generating TypeScript. We observe…

Large Language Model (LLM) agents have emerged as powerful tools for automating complex tasks by leveraging the reasoning and decision-making abilities of LLMs. However, a major bottleneck in current agent frameworks lies in the high…

We introduce latency-aware network acceleration (LANA) - an approach that builds on neural architecture search techniques and teacher-student distillation to accelerate neural networks. LANA consists of two phases: in the first phase, it…

Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for…

Personalizing visual generative models to meet specific user needs has gained increasing attention, yet current methods like Low-Rank Adaptation (LoRA) remain impractical due to their demand for task-specific data and lengthy optimization.…

Recent advance in sparse attention mechanisms has demonstrated strong potential for reducing the computational cost of long-context training and inference in large language models (LLMs). Native Sparse Attention (NSA), one state-of-the-art…

Artificial intelligence (AI) is increasingly deployed in real-time and energy-constrained environments, driving demand for hardware platforms that can deliver high performance and power efficiency. While central processing units (CPUs) and…

Recent advancements in Large Language Models (LLMs) have achieved robust performance across diverse tasks, but fine-tuning these models for specific domains remains resource-intensive. Parameter-Efficient Fine-Tuning (PEFT) methods like…

Large Language Model (LLM)-based multi-agent systems (MAS) demonstrate remarkable potential for scientific discovery. Existing approaches, however, often automate scientific discovery using predefined workflows that lack rationality…

Automated data preparation is crucial for democratizing machine learning, yet existing reinforcement learning (RL) based approaches suffer from inefficient exploration in the vast space of possible preprocessing pipelines. We present…

Vision-Language-Action (VLA) models have recently demonstrated impressive capabilities across various embodied AI tasks. While deploying VLA models on real-world robots imposes strict real-time inference constraints, the inference…

The proficiency of Large Language Models (LLMs) in coding tasks is often a reflection of their extensive pre-training corpora, which typically collapses when confronted with previously unfamiliar programming languages. Departing from…

We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against large language models (LLMs). MIA has emerged as a crucial technique for auditing privacy risks…

Small Language Models (SLMs) offer compelling advantages in deployment cost and latency, but their accuracy often lags behind larger models, particularly for complex domain-specific tasks. While supervised fine-tuning can help bridge this…

With recent advancements in natural language processing, Large Language Models (LLMs) have emerged as powerful tools for various real-world applications. Despite their prowess, the intrinsic generative abilities of LLMs may prove…

Transformer architectures have achieved remarkable success in various domains. While efficient alternatives to Softmax Attention have been widely studied, the search for more expressive mechanisms grounded in theoretical insight-even at…

Large Language Models (LLMs) have demonstrated remarkable performance in real-world applications. However, adapting LLMs to novel tasks via fine-tuning often requires substantial training data and computational resources that are…

Attention efficiency is critical to large language model (LLM) inference. While prior advances optimize attention execution for individual requests (e.g., FlashAttention), production LLM serving relies on batching requests with highly…

Latent factor models (LFMs) such as matrix factorization achieve the state-of-the-art performance among various Collaborative Filtering (CF) approaches for recommendation. Despite the high recommendation accuracy of LFMs, a critical issue…

Attention patterns play a crucial role in both training and inference of large language models (LLMs). Prior works have identified individual patterns such as retrieval heads, sink heads, and diagonal traces, yet these observations remain…