MLINFO COLLECTION
Modern image generation largely relies on specialized generative models that leave the process of image construction implicit in learned parameters. We explore an alternative: general-purpose coding…
Humanoid loco-manipulation requires coordinated whole-body interaction with the physical world, yet collecting robot demonstrations at scale remains costly. Human demonstrations offer a scalable…
Edge-cloud collaboration combines the lower inference overhead and greater data locality of edge-side execution with the stronger capabilities of cloud-hosted models. However, as LLM agents…
Long-horizon, semi-verifiable agentic tasks often rely on rubric-based evaluation, but the evidence needed to assess these tasks can be spread across the environment state and the execution trace. A…
LLM evolutionary search is currently evaluated by counting proposals (candidate programs). We demonstrate this metric hides the true cost of search, and redo the comparison using tokens.
We study packet routing in queuing systems where queues act as selfish, myopic agents that use no-regret learning algorithms to select servers with unknown service rates. To model the small buffers…
We prove that the last iterate of Optimistic Follow-The-Regularized-Leader (OFTRL) converges at a linear rate to a Nash equilibrium in multiplayer harmonic games. Our result holds under a mild…
Freshness shapes an LLM decision at the moment it is made; the action it commits to is latent, carried out later, in a changing world. We therefore introduce a timestamp theory of decision validity…
Training LLM agents to interact with users over multiple turns is challenging because the learning signal depends not only on the agent, but also on the user simulator and environment, which jointly…
このリポジトリは自然言語処理(NLP)に関するリソースをまとめたものです。
Conflict-graph search can stagnate despite effective operators when interventions fail to address the conflicts blocking progress. A disruptive intervention may also require further search before its…
We argue that tacit knowing is better modelled as an operating regime of a memory than as a kind of content. Our substrate is VaCoAl, an algebro-deterministic XOR-and-shift hyperdimensional memory…
home-llmは、ローカルLIMを使ってスマートホームの制御を可能にするHome Assistantの統合モデルです。
We study stationary discrete-time mean-field games with finite state and action spaces under the average-reward criterion, with an entropy-regularized objective and population-dependent dynamics and…
Safety-aligned large language models (LLMs) remain vulnerable to adversarial prompts that bypass their safety training. Existing automated red-teaming methods either require privileged access…
Harness self-evolution offers a practical route for LLM agents to improve from execution experience without updating model parameters. Its effectiveness depends on whether models can successfully act…
Conversational assistants are becoming the place where people ask what to buy, and sponsored content is moving into their answers. Several advertisers then compete for one sponsored slot, and all of…
We propose a new framework for banner ad auctions, leveraging diffusion models to allow for multiple bidders to co-win a single banner ad opportunity, and in particular influence the ad shown on the…
Reconstructing 3D scenes from sparse views without per-scene optimization remains highly challenging, especially for recovering accurate geometry and fine textures. While recent feedforward…
A predictor is multicalibrated with respect to a class of subpopulations (formally, of functions on the inputs, called auditors) if, for every subpopulation in the class and every value the predictor…
The Mallows model is a well-established construct in preference modeling, describing random rankings through their Kendall-Tau distance from a reference permutation. Its compact parameterization and…
We study multiwinner voting with $n$ voters and $m$ candidates, where the goal is to select a committee of size $k$. Voters have unit-sum cardinal utilities but report only coarse information induced…
Many machine learning approaches are two-level: an expert selects a class of methods, within this class the choice of key components is critical and usually manual. This paper addresses the automatic…
We study concurrent stochastic games in which a team of agents plays against an adversarial environment. If the agents could access a shared source of randomness, then these games reduce to…