The paper introduces onPanda, an interactive tool for efficiently annotating alignment data for large language models (LLMs) and agents. It uses token-level correction, allowing annotators to replace problematic tokens in model outputs, which reduces annotation time and preserves the model's natural output distribution.
The chart will appear after repeat observations. The current metric comes from the source.
2 source votesReal observations only. History before source connection is not reconstructed.
onPanda can help reduce the time required for data annotation while maintaining the model's natural output characteristics, making it useful for training alignment data efficiently.
IntBMoE introduces a block-conditioned Mixture-of-Experts (MoE) framework that decouples participation, execution, and materialization by combining dense expert composition with sparse block execution. It uses a learned codebook for blocks and a hypernetwork to merge experts, achieving full participation while keeping execution and memory costs low. Experiments show improvements in image classification, language modeling, and sequential recommendation, with real-world deployment in AMap's recommendation system.
4 days agoDaily PapersThis paper evaluates the ability of the MiniMax-H3 multimodal generative model to reason about the physical world. The study introduces a new framework for assessing physical reasoning through four dimensions, using tasks that require integrating information across multiple modalities. The model achieves an overall success rate of 41.97% across 517 evaluation instances, with video-based reasoning performing best and audio-based reasoning least effectively.
6 days agoDaily PapersThe paper introduces SELF-INDEX, a framework that enables an index to self-evolve without human intervention by autonomously diagnosing retrieval issues, revising index keys, and validating changes. It also uses a Query Simulator to proactively explore new retrieval demands, improving performance across various corpora and downstream applications.
5 days agoDaily PapersThe paper introduces ScienceIDE, a framework that transforms scientific code repositories into programmable environments for training scientific agents. These environments enable task generation, execution, and verification, supporting supervised fine-tuning and reinforcement learning. The approach demonstrates improvements in scientific code repair and general-purpose benchmarks.
6 days agoDaily PapersThe paper identifies a problem called Value Flattening in Proximal Policy Optimization (PPO) critics, where estimated state values change sharply while critic predictions remain flat. It introduces SP^3O, a method that applies value loss to only a few states per response, showing improvements in policy learning.
6 days agoDaily PapersThe paper introduces ActionPiece, a method for autoregressive vision-language-action models that improves action tokenization by preserving physical action relationships through joint supervision of representation learning and quantization. It uses physical rank consistency (PRC) to measure how well tokenization maintains local physical distance rankings after reconstruction, and shows improvements in policy success on multiple benchmarks.
6 days ago