paper-with-me

Papers

TESS 2: A Large-Scale Generalist Diffusion Language Model

2025-02-19 · Jaesung Tae, Hamish Ivison, Sachin Kumar, Arman Cohan

We introduce TESS 2, a general instruction-following diffusion language model that outperforms contemporary instruction-tuned diffusion models, as well as matches and sometimes exceeds strong autoregressive (AR) models. We train TESS 2 by first adapting a strong AR model via continued pretraining with the usual cross-entropy as diffusion loss, and then performing further instruction tuning. We find that adaptation training as well as the choice of the base model is crucial for training good instruction-following diffusion models. We further propose reward guidance, a novel and modular inference-time guidance procedure to align model outputs without needing to train the underlying model. Finally, we show that TESS 2 further improves with increased inference-time compute, highlighting the utility of diffusion LMs in having fine-grained controllability over the amount of compute used at inference time. Code and models are available at https://github.com/hamishivi/tess-2.

📄 PDF Abstract BibTeX arXiv:2502.13917

Code (1)

hamishivi/tess-2 공식 구현 pytorch

Tasks

Instruction FollowingLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
BASE 설명 없음

Similar Papers 제목 키워드 기반

TESS: Text-to-Text Self-Conditioned Simplex Diffusion

2023-05-15 · Rabeeh Karimi Mahabadi, Hamish Ivison, Jaesung Tae, James Henderson 외

Diffusion models have emerged as a powerful paradigm for generation, obtaining strong performance in various continuous domains. However, applying continuous diffusion models to natural language remains challenging due t…

Natural Language UnderstandingParaphrase GenerationQuestion GenerationQuestion-Generation+2

Diffusion Model as a Generalist Segmentation Learner

2026-04-27 · Haoxiao Wang, Antao Xiang, Haiyang Sun, Peilin Sun 외 arxiv

Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors. In this paper, we demonstrate that these priors can be utilized for text-conditio…

Semantic Segmentation

Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks

2022-10-27 · Edwin Zhang, Yujie Lu, Shinda Huang, William Wang 외

Training generalist agents is difficult across several axes, requiring us to deal with high-dimensional inputs (space), long horizons (time), and generalization to novel tasks. Recent advances with architectures have all…

reinforcement-learningReinforcement Learning (RL)

Beyond Sight: Finetuning Generalist Robot Policies with Heterogeneous Sensors via Language Grounding

2025-01-08 · Joshua Jones, Oier Mees, Carmelo Sferrazza, Kyle Stachowicz 외

Interacting with the world is a multi-sensory experience: achieving effective general-purpose interaction requires making use of all available modalities -- including vision, touch, and audio -- to fill in gaps from part…

Robot ManipulationText GenerationVision-Language-Action

Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks

2022-11-17 · CVPR 2023 1 · Hao Li, Jinguo Zhu, Xiaohu Jiang, Xizhou Zhu 외

Despite the remarkable success of foundation models, their task-specific fine-tuning paradigm makes them inconsistent with the goal of general perception modeling. The key to eliminating this inconsistency is to use gene…

DecoderLanguage ModellingMulti-Task Learning