5). Scaled-up Instructable Model Become Less Reliable – suggests that larger and more instructable LLMs may become less reliable; investigates LLMs across three elements: difficulty concordance, task avoidance, and prompting stability…
@dair_ai
-
Large Language Models Struggle with Domain-Independent Planning Tasks
By
–
4). LLMs Still Can’t Plan – evaluates whether large reasoning models such as o1 can plan; finds that a domain-independent planner can solve all instances of Mystery Blocksworld but LLMs struggle, even on small instances…
-
AlphaChip: Reinforcement Learning Designs Google TPU Physical Layout
By
–
3). AlphaChip – a reinforcement learning-based method trained to design the physical layout of chips; AlphaChip is reportedly used in three additional generations of Google’s TPU…https://t.co/kM6HcgSTj4
— DAIR.AI (@dair_ai) 29 septembre 20243). AlphaChip – a reinforcement learning-based method trained to design the physical layout of chips; AlphaChip is reportedly used in three additional generations of Google’s TPU…
-
LLM Peak Performance: Training, Inference, System Optimization
By
–
10). Achieving Peak Performance for LLMs – a systematic review of methods for improving and speeding up LLMs from three points of view: training, inference, and system serving; summarizes the latest optimization and acceleration strategies around training, hardware, scalability,
-
Flash-Sigmoid: Hardware-Efficient Attention 17% Faster
By
–
9). Theory, Analysis, and Best Practices for Sigmoid Self-Attention – proposes Flash-Sigmoid, a hardware-aware and memory-efficient implementation of sigmoid attention; it yields up to a 17% inference kernel speed-up over FlashAttention-2 on H100 GPUs; show that SigmoidAttn
-
Can LLMs Generate Novel Scientific Research Ideas
By
–
8). Can LLMs Unlock Novel Scientific Research Ideas – investigates whether LLM can generate novel scientific research ideas; reports that Claude and GPT models tend to align more with the author's perspectives on future research ideas; this is measured across different domains
-
Small Language Models Role Applications in LLM Era
By
–
6). The Role of Small Language Models in the LLM Era – closely examines the relationship between LLMs and SLMs; common applications of SLMs include data curation, training stronger models, efficient inference, evaluators, retrievers, and much more; includes insights for
-
Agent Workflow Memory for Autonomous Learning Systems
By
–
5). Agent Workflow Memory – introduces Agent Workflow Memory to induce commonly reused workflows and provide these to the agent on demand; works offline and online and is meant to guide the agent's subsequent generations; it’s inspired by how humans learn reusable workflows from
-
LLaMa-Omni: Low-Latency Speech-to-Speech LLM Model Architecture
By
–
7). LLaMa-Omni – a model architecture for low-latency speech interaction with LLMs; it is based on Llama-3.1-8B-Instruct and can simultaneously generate both text and speech responses given speech instructions; responses can be generated with a response latency as low as 226ms…
-
DataGemma: Fine-tuned Gemma 2 Models for Statistical Data
By
–
4). DataGemma – includes a series of fine-tuned Gemma 2 models to help LLMs access and incorporate numerical and statistical data; proposes a new approach called Retrieval Interleaved Generation (RIG) which can reliably incorporate public statistical data from Data Commons into