REVIEW 15 cited by
Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning
read the original abstract
The recent surge of generative AI has been fueled by the generative power of diffusion probabilistic models and the scalable capabilities of large language models. Despite their potential, it remains elusive whether diffusion language models can solve general language tasks comparable to their autoregressive counterparts. This paper demonstrates that scaling diffusion models w.r.t. data, sizes, and tasks can effectively make them strong language learners. We build competent diffusion language models at scale by first acquiring knowledge from massive data via masked language modeling pretraining thanks to their intrinsic connections. We then reprogram pretrained masked language models into diffusion language models via diffusive adaptation, wherein task-specific finetuning and instruction finetuning are explored to unlock their versatility in solving general language tasks. Experiments show that scaling diffusion language models consistently improves performance across downstream language tasks. We further discover that instruction finetuning can elicit zero-shot and few-shot in-context learning abilities that help tackle many unseen tasks by following natural language instructions, and show promise in advanced and challenging abilities such as reasoning.
Forward citations
Cited by 15 Pith papers
-
Large Language Diffusion Models
LLaDA is a scalable diffusion-based language model that matches autoregressive LLMs like LLaMA3 8B on tasks and surpasses GPT-4o on reversal poem completion.
-
Understanding Parallel Samplers in Masked Diffusion via Random Walks on Graphs
Graph random walks provide a verifiable sandbox for diagnosing parallel samplers in masked diffusion models, showing performance depends on graph structure and introducing a new exact bisection sampler.
-
Relative Score Policy Optimization for Diffusion Language Models
RSPO interprets reward advantages as targets for relative log-ratios in dLLMs, calibrating noisy estimates to stabilize RLVR training and achieve strong gains on planning tasks with competitive math reasoning performance.
-
Leveraging Pretrained Language Models as Energy Functions for Glauber Dynamics Text Diffusion
Pretrained language models are used as energy functions for Glauber dynamics in discrete text diffusion, improving generation quality over prior diffusion LMs and matching autoregressive models on benchmarks and reaso...
-
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding
Fast-dLLM adds reusable KV cache blocks and selective parallel decoding to diffusion LLMs, closing most of the speed gap with autoregressive models without retraining.
-
Diffusion and Flow Matching Models for Tabular Data: A Survey
First dedicated survey organizing diffusion and flow matching models for tabular data synthesis, imputation, anomaly detection, and related tasks, covering literature from 2015 to 2026 and highlighting open problems.
-
Towards A Generative Protein Evolution Machine with DPLM-Evo
DPLM-Evo is an evolutionary discrete diffusion framework that models protein sequences via explicit substitution, insertion, and deletion operations, achieving state-of-the-art single-sequence mutation effect predicti...
-
Towards A Generative Protein Evolution Machine with DPLM-Evo
DPLM-Evo adds explicit edit operations and a latent alignment space to discrete diffusion protein models, achieving SOTA single-sequence mutation effect prediction on ProteinGym while supporting variable-length generation.
-
Towards A Generative Protein Evolution Machine with DPLM-Evo
DPLM-Evo introduces an evolutionary discrete diffusion framework with explicit edit prediction and contextual noising that claims SOTA single-sequence mutation effect prediction on ProteinGym while supporting variable...
-
Measuring Temporal Linguistic Emergence in Diffusion Language Models
In diffusion language models, coarse linguistic labels stabilize earlier than exact token identity, uncertainty tracks correctness, and mid-trajectory states are most sensitive to perturbations.
-
Dream 7B: Diffusion Large Language Models
Dream 7B is a 7B diffusion LLM that refines sequences in parallel via denoising and outperforms prior diffusion models on general, mathematical, and coding benchmarks with added flexibility in generation order and qua...
-
LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning
LLaDA-V is a diffusion-based multimodal large language model that reaches competitive or state-of-the-art results on visual instruction tasks while using a non-autoregressive architecture.
-
Scaling Diffusion Language Models via Adaptation from Autoregressive Models
Adapting autoregressive models via continual pre-training yields diffusion language models from 127M to 7B parameters that outperform prior diffusion models and compete with their autoregressive counterparts on langua...
-
A Theoretical Analysis of Memory and Overfitting Phenomena in Stochastic Interpolation Models
In the oracle continuous-time setting, stochastic interpolation models recover training samples exactly, with deviations controlled by discretization and estimation errors, leading to theoretical definitions of overfi...
-
Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention
BA-Att introduces pre-downsampled block selection with norm-sorting and diagonal covariance correction to approximate sparse attention, yielding up to 6.95x speedup at 50% sparsity across language, multimodal, and vid...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.