Media
AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection Y ujin Wang
Image Signal Processors (ISPs) play a fundamental role in camera systems.
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
Limitations in either capability can impede the overall performance of a VLM. A systematic evaluation of the perception and reasoning capabilities is crucial to provide valuable insights for future model optimization.
LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes
Neural Radiance Fields (NeRFs) have shown remarkable performances in producing novel-view images from high-quality scene images.
Consent in Crisis: The Rapid Decline of the AI Data Commons
The web has become the primary communal source of data, or "data commons", for general-purpose
xLSTM: Extended Long Short-Term Memory Maximilian Beck
Since then, LSTMs have stood the test of time and contributed to numerous deep learning success stories, in particular they constituted the first Large Language Models (LLMs). However, the advent of the Transformer technology with parallelizable self-attention at its core marked the dawn of a new era, outpacing LSTMs at scale.
Risk-Averse Fine-tuning of Large Language Models Sapana Chaudhary Amazon Web Services (A WS)
The deployment of large language models (LLMs) is witnessing remarkable growth across both personal and professional domains [Nakano et al., 2021, Touvron et al., 2023].
Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees Sijia Chen 1, 2, Yibo Wang 1, 2, Yi-Feng Wu3 Qing-Guo Chen
Tool-augmented large language models (LLMs) leverage tools, often in the form of APIs, to improve their reasoning capabilities on complex tasks. This enables them to act as intelligent agents interacting with the real world. The recently introduced ToolLLaMA model by Qin et al. [ 2023 ] utilizes the depth-first search-based decision tree (DFSDT) mechanism for multi-step reasoning with 16000+ real-world APIs, effectively enhancing the performance of tool-augmented LLMs compared to traditional chain reasoning mechanisms. However, their approach only employs successful paths from decision trees (also called inference trees) for supervised fine-tuning (SFT), missing out on the potential learning opportunities from failed paths. Inspired by this, we propose an inference trajectory optimization framework based on preference learning to address this limitation.
Large Language Model Unlearning
We study how to perform unlearning, i.e. forgetting undesirable (mis)behaviors, on large language models (LLMs).
The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models Hannah Rose Kirk 1
Human feedback is central to the alignment of Large Language Models (LLMs).
AI-generated Text Detection by Checking Memorization of Preceding Tokens
Given a piece of subject text, many existing detection methods work by measuring the difficulty of LLM predicting the next token in the text from their prefix.