preprint
8 notes, newest first.
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World
The paper presents an interactive video world model that keeps track of a scene's state outside the model itself (an externally stored, camera-indexed memory) so it does not need to hold everything in context, aiming…
DreamX-Phi 1.0: Action-Conditioned Video World Model for Robotic Manipulation
The paper describes a model that, given a starting camera frame, a language instruction, and a planned sequence of robot actions, predicts what the robot's camera would see next, intended to help with robotic…
Intern-S2-Preview: Scientific Agentic Foundation Model
The paper introduces a family of foundation models trained specifically for multimodal scientific work, using scientific documents, interleaved image-text data, and diverse scientific corpora, with a large…
Benchmarking LLM Judges for Mobile Agent Evaluation
A benchmark study of LLM judges used to evaluate mobile-agent trajectories.
MBA: Multimodal Benchmark and Agents for Real-World Business Ideation
A multimodal benchmark and training setup for agents that generate and evaluate business ideas using visual evidence.
Who Thinks Best Depends on How Long You Let Them: Budget-Dependent Rankings in LLM Evaluation
An evaluation study examining how token budgets affect model accuracy and comparative rankings.
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
The paper argues no single LLM is optimal for every query or budget, and proposes a standard framework plus open-source toolkit for building, testing, and deploying systems that route each query to the most suitable…
DarwinX: Evolving Agent Harnesses Through Natural Selection
The paper proposes improving AI agents not by changing the underlying model weights, but by evolving the surrounding "harness" (prompts, tools, workflow scaffolding) through a selection process across a population of…
