📊AI Paper Daily

Issue 112

Wed, 11 Nov 2026

10 papers

Weight-space programming, introduced in recent MIT work by Takehi et al., enables a frontier LLM agent to read a network's weights and write a repair. Their GPT-6 Astra agent corrected the reasoning l...
Few-step sampling reduces the cost of streaming video generation. Distribution Matching Distillation (DMD) supervises few-step generators with a separate fake-score network, which adds training memory...
System-1 Decision Models directly make structured probabilistic decisions over query-specified options given a state in a single forward pass, without autoregressively generating reasoning trajectorie...
Dexterous manipulation requires rich spatial foresight over both the surrounding scene and the robot hand. Existing world-action models often acquire such predictive knowledge through explicit future ...
Software agents built on large language models generate traffic unlike human web traffic, yet routers have no class for it and cannot verify a sender's claim to be an agent. This paper proposes the Ve...
Taxonomies are structured knowledge representations that support semantic search, recommendation, product catalog organization, and retrieval-augmented generation. Their automated construction from a ...
Memory-augmented vision-language-action (VLA) policies are meant to remember what happened. Many of them, however, fill memory by time: they sample frames uniformly across the episode and stamp each f...
Much of the variation in financial time series is driven by market-wide shocks that cannot be predicted from an asset's own history. Per-asset self-supervised learning treats this variation as irreduc...
Predicting long action chunks, often spanning dozens of timesteps, has become a key ingredient in increasingly capable robot policies. In this paper, we find that adapting these long-chunk policies wi...
RLVR trains language models to reason by rewarding correct final answers. A widely used algorithm, group-relative policy optimization (GRPO), gives every token of a solution the same credit, so dense ...