Research Feed

Magpie is a real-time renderer that uses foundation models to generate game visuals by processing white-box frames as a continuous denoising condition.

The paper introduces a layered composition framework for semantic data processing that integrates online learning components to reduce the cost of LLM-based query execution.

CritICL improves large language model performance by providing targeted, failure-aware critique examples in the prompt to steer reasoning away from common pitfalls.

The PILOT harness allows AI agents to improve their performance in real time by employing a supervisor that provides live feedback and distills successful strategies during task execution.

The paper introduces Agent Mesh to address unique reliability challenges in agentic software development by defining new primitives to manage non-idempotent tool delegations.

The paper introduces scrydb to enable combined lexical and semantic search capabilities within a single SQLite database file.

StreamPI adds historical context to vision-language-action models to improve robotic task performance without increasing the model parameter count.

VoiceMem is a dual-brain architecture designed to provide accurate, low-latency memory retrieval for speech-based conversational agents.

Prefix Sliding enables large language models to perform reasoning tasks three times faster without requiring additional training.

JIT-Agent improves agent performance by dynamically generating and evolving task-specific control structures just in time to meet individual task demands.

ProgRouter optimizes multi-agent workflows by dynamically selecting models based on progress and cost to maximize task completion rates within defined energy budgets.

LeFlow optimizes action planning by using a generative model to predict future trajectories, significantly reducing computation time compared to traditional iterative methods.

The Gated Recurrent Transformer reduces memory usage and parameter count by replacing many unique transformer layers with a single shared, repeating block.

The paper introduces a causal state-space model for video anomaly detection that runs directly on edge hardware without needing frame buffering.

The Multi-Specialist LLM Relay System improves coding agent performance by using specialized agents and a staged pipeline to solve complex programming tasks.

ExTS improves search efficiency by adapting tree search strategies based on diagnostic pilot runs that characterize the search landscape.

The LAWA architecture optimizes robot action planning by using latent intentions to reduce inference latency while maintaining high success rates across robotics benchmarks.

The paper introduces a scalable framework called RACE that uses statistical estimation to identify functionally consistent neurons in LLMs with significantly lower computational overhead than traditional methods.

The authors introduce a family of sparse embedding models that leverage Mixture-of-Experts architectures and distillation to achieve high throughput and competitive retrieval performance.

The Physics Attention Transformer predicts tokamak plasma instability growth rates faster by replacing slow traditional solvers with a learned neural architecture.