Category
20,463 papers
It is argued that continual prompt evolution is a practical, training-free alternative to retraining for multimodal forecasting.
On-policy learning is central to post-training: training on a model's own generations limits distribution shift and helps preserve existing capabilities. On hard problems, however, on-policy RL provides no reward-based learning signal when all attempts fail. On-policy distillation provides next-token supervision from a...
Vector-Borda Empirical-Gap Elimination (VB-EGE) is presented, a fixed-confidence adaptive sampling algorithm for efficiently identifying models on the Pareto frontier in arena-style evaluation and established a worst-case lower bound showing that VB-EGE is minimax-optimal up to logarithmic factors.
Solving reasoning tasks supported on graphs typically requires providing a Language Reasoning Model (LRM) with a serialized description of the graph. This approach results in the input length growing with the number of edges, which limits the size of the problems that can be solved. Furthermore, even when graphs fit in...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces $MLIPS: a training-free method that shares candidate search while retaining each consumer's own scoring and selection, and characterize this shared working-set structure and use it to motivate Top-$G, an exploratory bounded pool construction for prefill.
Mixture-of-experts (MoE) models already make a sparse choice for every token: which experts should process it. We ask whether a sparse dictionary should reuse that choice. NR-SAE gives each routed expert a small dictionary and opens only those the frozen router selects. At block 15 of Gemma 4 26B-A4B, after ten million...
This work formalizes the interaction between AI systems and users as a game with three players: a defender and an attacker that are computationally or informationally bounded, and an AI that provides public advice and is less constrained.
We study trail-weighted pruning of evidence for Bayesian-network prediction. A traversal enumerates the active trails from each evidence node to the outcome, scores each trail by the product of its edge strengths, and drops evidence whose score falls below a threshold. For collider-free networks (chains and forks) over...
The predictive closure characterization is proposed, which accounts for the relationships between features and shows that unpredictable features can become better represented when they help predict other features, and that changing one feature's predictive relationships can affect how well others are represented.
Scaling laws suggest that increasing model size, training data, and compute generally yields monotonic performance improvements. While this often holds at the aggregate level, we present systematic evidence that vision-language models (VLMs) exhibit inverse scaling at the subtask level: specific question categories on...
Byzantine-robust aggregation shields federated learning from malicious updates, but the rules that filter out suspect updates do so by comparing clients' parameter vectors. That comparison requires access to every client's update, which secure aggregation exists to withhold, costs $O(n^2 d)$ in the parameter dimension...
Beneath the apparent diversity of foundation models lies an increasingly homogeneous technical stack of common training pipelines, distillation methods, and data. These shared algorithmic choices can expose an otherwise distinct model ecosystem to concentrated risks leading to a vulnerability monoculture. Yet current p...
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.
