Papers

Listen to this article.

Only the latest audio is kept; older files are removed on each update.

Problem

Autonomous AI agents are showing promise in conducting machine learning research. However, these agents often lack “operational knowledge”—the practical, domain-specific know-how that bridges the gap between understanding a technique and applying it effectively. This knowledge currently resides in the vast landscape of code repositories and research papers, but it’s scattered, difficult to access, and too large to efficiently use during task execution.

Listen to this article.

Only the latest audio is kept; older files are removed on each update.

Problem

Training AI tutors that adapt to individual student needs is incredibly valuable, but gathering data on what tutoring methods work best for each student is currently difficult – both time-consuming and expensive. Existing solutions haven’t fully cracked the code: some student simulators accurately model behavior but fail at understanding explanations, while others excel at following guidance but aren’t very good at mimicking actual student competence.

Listen to this article.

Only the latest audio is kept; older files are removed on each update.

Problem

Existing video generation models frequently treat audio and visuals as separate components, either omitting audio entirely or generating it in a later step. This disconnected approach misses the opportunity to model how visual elements and sounds naturally influence each other within a scene. DreamX-Creator aims to tackle this by enabling joint audio-video generation – creating both sight and sound simultaneously from a single input.

Listen to this article.

Only the latest audio is kept; older files are removed on each update.

Problem

Large language models (LLMs) are increasingly being used in complex, multi-step tasks that require them to manage lots of information across many turns. The standard approach – storing all previous interactions as context – quickly becomes unsustainable because the context window grows and grows. Existing “proactive context management” techniques try to solve this by allowing LLMs to edit their own working memory (e.g., searching, deleting, or summarizing). However, these methods are limited; they offer a basic toolset, don’t support complex planning or long-term memory, and struggle with how to best learn which edits are most effective during training.

Listen to this article.

Only the latest audio is kept; older files are removed on each update.

Problem

Current vision-language models excel at recognizing and describing physical events, but they struggle with the deeper task of reasoning about how those events unfold and how to predictably influence them. This boils down to a lack of explicit representation of the underlying physics – things like object states, how objects interact (dynamics), and measurable parameters governing their behavior. Essentially, these models understand what happens but not necessarily why.

Listen to this article.

Only the latest audio is kept; older files are removed on each update.

Problem

Scaling world models – AI systems that understand and predict environments – typically relies on feeding them vast amounts of video data alongside significant computational resources. This paper argues that this approach is inefficient because it lacks a crucial element: reliable, grounded reward signals to guide learning after initial training (often referred to as “post-training”). Current methods for assessing spatial generation quality often rely on fuzzy proxies like CLIP scores which are prone to bias and don’t effectively support Reinforcement Learning (RL).

Listen to this article.

Only the latest audio is kept; older files are removed on each update.

Problem

Vision-language-action (VLA) models are increasingly popular for creating generalist embodied agents – robots that can understand instructions, perceive their surroundings visually, and take actions in the real world. However, a key question remains: can we build even better VLA systems by rethinking their architecture and training them on more data? Current models may not be effectively leveraging architectural designs or scaling to truly massive datasets with varied types of data. Ultimately, existing systems might struggle to generalize well across different robots (“embodiments”) and tasks.

Listen to this article.

Only the latest audio is kept; older files are removed on each update.

Problem

Current large language models (LLMs) are impressive at reasoning and knowledge synthesis, but fall short when tackling complex real-world tasks that require sustained effort and interaction with external tools and data sources. This paper identifies a gap in the ability of LLMs to make sustained, verifiable progress towards long-term objectives—what they call “working capability”. Think about projects involving multiple files, searching online for information, running code, remembering what’s been done already, handling errors, and producing reliable results.

Listen to this article.

Only the latest audio is kept; older files are removed on each update.

Problem

Large Language Model (LLM) agents, enhanced with “skills” – essentially structured knowledge packages – have shown promise in improving task completion rates at runtime. However, there’s a gap in understanding why these skills work, and crucially, when they don’t. Existing evaluations largely focus on overall success, neglecting the underlying mechanisms that drive skill effectiveness. This paper aims to explore those nuances.

Listen to this article.

Only the latest audio is kept; older files are removed on each update.

Problem

Evaluating world models – AI systems that simulate and reason about environments – is currently a flawed process. Existing benchmarks typically provide only a single score, offering little insight into why the model performed well or poorly. Understanding the underlying reasoning behind these scores, especially concerning factors like physics, causality, and accurate state changes within the simulated world, is crucial for improving model reliability. Current methods lack transparency, essentially providing black-box evaluations with no explanation of how those scores were derived.

Papers

Paper: Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Problem

Paper: StudentSim: Training LLM-based Student Simulators

Problem

Paper: DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution

Problem

Paper: ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

Problem

Paper: Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

Problem

Paper: Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Problem

Paper: GigaBrain-0.7: Scaling Embodied Foundation Models to Emergent Capabilities with a Three-System Ar...

Problem

Paper: Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Problem

Paper: Demystifying Agent Skills: Why They Work-Until They Don't

Problem

Paper: HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Problem