Category
20,463 papers
Classifier-free guidance (CFG) is a standard component of conditional diffusion models, and guided generation performance has become the \textit{de facto} measure of state-of-the-art models. Recent work on latent diffusion models seeks to learn latent spaces that are easier to model with diffusion. However, under CFG,...
Standard autoregressive decoding advances one token at a time, even when several upcoming tokens can be predicted together. We propose CADENCE (Context-Adaptive DEcoding), a generation method that learns both what to draft and how far to draft. Gaussian prediction heads represent future spans as continuous latent vecto...
Findings support incorporating price geometry and volume into generative modeling, with field accuracy and predictive uncertainty evaluated together, in a full-field evaluation framework that combines a transport cost sensitive to price placement and total volume with proper scoring rules and calibration diagnostics.
Forecasting an unresolved event requires finding relevant evidence and deciding how strongly it supports each outcome. Yet outcome-based training of Large Language Model (LLM) forecasters often begins with preassembled evidence at a single prediction date, leaving evidence acquisition outside the learning loop. We intr...
Reach audiences
Advertise in front of researchers, engineers, and readers.
Most freeway agencies have fixed detectors on only part of their network but need speeds for all of it. This paper compares methods for estimating current and next-hour speeds on every link from such sparse detectors, using historical probe data for training. The test network is the Dallas--Fort Worth freeway system: 4...
This work evaluates how accurately large Language Models predict the impact of self-generated ML experiment ideas before these are put into training runs to show that current LLMs have useful but limited intuition about which ML ideas will work.
This paper observes that when a safe model is recursively self-distilled on its own (safe) generations while receiving an additional non-harmful cue, it becomes increasingly misaligned across a diverse set of harmful queries; it is called Progressive Misalignment.
This work introduces Sparse Autoencoder Geometric Anchoring (SAGA), which converts a Sparse Autoencoder (SAE) trained at each task boundary into local, low-rank constraints on representation drift, and establishes its local relation to latent code matching, define its spectral truncation error, and derive a conditional...
Transformer Residual Activation Codebook Encoding (Trace), a framework that eliminates the received data downstream computation and enables communication--computation overlap and reduces a key latency bottleneck in distributed Transformer inference.
This study investigates whether Large Language Models, conditioned on physical diagnostic descriptions of simulation errors, can propose informative parameter updates more efficiently than conventional derivative-free optimizers, and introduces a hybrid workflow that uses the LLM as a warm-start, passing accumulated ev...
A conceptual framework linking data quality assurance, feature engineering, model training and reliability testing, and deployment to an agent population is proposed, closed by a cross-agent monitoring and feedback loop.
It is concluded that horizontally scalable, log-based messaging, combined with fault-tolerant, in-memory and micro-batch computation and durable, replicated storage constituted the technical foundation that made real-time, ML-driven enterprise analytics feasible within this period and that this layered architecture con...
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
