Research Feed Page 3

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 paper introduces ZID, a new evaluation metric for generative models that identifies and ranks failures in image generation where traditional metrics like FID fail.

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.

FedV-KGQA enables multi-hop reasoning over knowledge graphs distributed across different organizations by fusing local entity embeddings without sharing private raw data.

The paper introduces notlob, a system that maintains a graph of prose and code to improve how coding agents navigate and manage development context.

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.

SPO++ is a refined policy optimization framework that increases online learning efficiency for language agents by aligning data tracking with event timing.

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 paper introduces a constraint-based verification method that filters LLM responses against knowledge graph logic to significantly improve answer precision without sacrificing recall.

WarpSAC is a scalable reinforcement learning framework that adapts its architecture based on available compute resources to accelerate training and improve deployment success.

The paper introduces IAPO, a method that improves agent training by redistributing reward credit based on how agent actions influence one another within multi-turn service workflows.

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

Researchers evaluated how medical Large Language Models reason by systematically perturbing inputs and measuring if the model's logical chain stays consistent with its final output.

Researchers built an open-world multi-agent system that autonomously explores complex mathematical problems by having independent agents read, write, and verify findings in a shared research environment.

The paper introduces a Mixture of Task Experts architecture that uses task-specific modules within a video-language decoder to improve performance across diverse video understanding tasks.

The study evaluates how different quantization formats impact the performance of large language models when processing the Bangla language across various natural language understanding benchmarks.