autoregressive model
PulseAugur coverage of autoregressive model — every cluster mentioning autoregressive model across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
Autoregressive vs. Diffusion Models: AI Writing Approaches Compared
Two distinct approaches to AI text generation are autoregressive models and diffusion models. Autoregressive models generate text token by token, with each new token depending on the preceding ones, making them suitable…
-
Energy-Based Models Unify Diverse Machine Learning Approaches
A new tutorial paper published on arXiv explores machine learning through the lens of energy-based models (EBMs). It proposes that EBMs, which define distributions via a scalar energy function, can unify various machine…
-
Paper frames generative AI via stochastic dynamics, LLMs, and neural SDEs
A new paper explores generative AI through the lens of stochastic dynamical systems, examining three distinct model classes. It formulates large language models (LLMs) as nonlinear autoregressive models, offering a prob…
-
Discrete diffusion models show planning advantages over autoregressive models
A new research paper explores the advantages of discrete diffusion models over autoregressive models in planning tasks. By abstracting planning into graph traversal problems, the study found that non-autoregressive mode…
-
Tutorial Explores Generative Models for Music Audio Creation
This tutorial paper provides a comprehensive overview of generative models used for music audio creation, targeting readers familiar with neural network training but new to music generation. It details various methods i…
-
VC Dimension of Autoregressive LTFs Resolved, Stochastic Models Show Exponential Gap
Researchers have resolved a long-standing gap in understanding the VC dimension of autoregressive Linear Threshold Functions (LTFs). For deterministic autoregressive LTFs, the VC dimension has been proven to be Θ(d^2) f…
-
New LAW technique enables pure self-conditioning for language models
Researchers have developed a new language modeling technique called LAW (Loopholing All the Way) that relies purely on self-conditioning. This method propagates expected embeddings through the denoising process, decodin…
-
Block Diffusion Models Show Promise for Longitudinal EHR Analysis
Researchers have explored block diffusion (BD) as an alternative to autoregressive (AR) models for predicting from longitudinal electronic health records (EHR). While AR models excel at zero-shot prediction, they strugg…
-
New CoRAL framework merges diffusion and autoregressive models for efficient multimodal reasoning
Researchers have introduced CoRAL, a novel hybrid framework designed to overcome the limitations of both autoregressive models (ARMs) and diffusion language models (DLMs) in multimodal reasoning. CoRAL employs an Asymme…
-
Stanford researchers unveil Next-Concept Modeling for AI language generation
Researchers from Stanford University's Hazy Research group have introduced Next-Concept Modeling (NCM), a novel language generation architecture. Unlike traditional autoregressive models that produce text token by token…
-
Text-to-Image Synthesis: A Decade Survey Paper Published
A comprehensive survey paper reviews 490 research papers on text-to-image synthesis (T2I) published over the last decade, with coverage extending to 2026. The paper details the evolution of generative models like GANs, …
-
New research tackles variational inference challenges in AI
Two new research papers address challenges in variational inference, a method used for approximating complex probability distributions. The first paper, "Mode Collapse of Mean-Field Variational Inference," provides a th…
-
Next-Concept Modeling accelerates text generation with parallel, coarse-to-fine approach
Researchers have introduced Next-Concept Modeling (NCM), a novel two-stage framework designed to accelerate text generation. NCM utilizes a multiscale residual VQ-VAE to encode text into a hierarchy of discrete codes, w…
-
New framework GeoSim analyzes VLM representations for image restoration
Researchers have developed a new framework called GeoSim to analyze the internal representations of vision-language models (VLMs) for low-level image restoration tasks. The study investigates how different VLM architect…
-
AI Video Generation Better Aligns with Human Visual Cortex
Researchers have developed a new method to evaluate video generation models by comparing their internal representations to human visual cortex activity. They found that autoregressive (AR) video diffusion models, when g…
-
New SPRINT model generates recommendations in single step, boosting efficiency and accuracy
Researchers have introduced SPRINT, a novel single-step generative recommendation system that bypasses the token-by-token generation common in existing autoregressive and non-autoregressive models. By viewing item recom…
-
Diffusion language models achieve over 1,000 tokens/sec speed
Diffusion language models are emerging as a new paradigm, capable of generating text at speeds exceeding 1,000 tokens per second. This marks a significant shift from traditional autoregressive models, which generate tex…
-
AI startup VIDRAFT unveils AX-RAY to detect hidden causal leakage in models
VIDRAFT, an AI safety startup, has developed a new auditing framework called AX-RAY to detect causal leakage in hybrid sequence models. This leakage occurs when future token information improperly influences earlier pos…
-
MegaParts scales 3D object generation to 300 parts using token-efficient autoregressive modeling
Researchers have developed MegaParts, a novel framework for 3D object generation that significantly scales part-aware modeling. By employing token-efficient vector-quantized part tokens and structured autoregressive seq…
-
New LHSDet method detects high-resolution AI-generated images using VQA
Researchers have developed LHSDet, a new method for detecting high-resolution AI-generated images. This approach reframes the detection task as a visual question answering problem, utilizing a vision-language framework.…