Papers
Browse the full research library.
Ten papers per page, with summaries, diagrams, formulas, concepts and citations kept close to the source.
Efficient Scalable Oversight via Rewinding
New proof-system model for scalable AI oversight: checkpoint and rewind the prover to verify robust oracle computations with no cryptography and no truthful-prover assumption.
Read this for a deep treatment of scalable oversight, interactive proof systems, oracle robustness, verifier soundness, checkpointed AI execution and the gap between theoretical guarantees and deployable AI verification.
Ziyi Guan, Yael Tauman Kalai, Ron Rothblum
Read paper
LoGRA: Low-Rank Gradient Sketches for Memory-Efficient LLM RL
LoGRA is a memory-efficient LLM reinforcement learning method using low-rank gradient sketches, projection refreshing, and KL-controlled updates to reduce GPU memory during RL post-training.
Read this LoGRA explainer for a practical guide to low-rank gradient sketches, memory-efficient LLM reinforcement learning, gradient compression, projection rank, RowAdam, predicted-KL control, and the limits of the reported 1.5B, 7B, and 27B experiments.
Shaokun Zhang, Yifan Zhang, Jian Hu
Read paper
LongHarness
A stateful agent harness that couples source-linked evidence with evolving conclusions to improve grounded reasoning over document corpora exceeding 100 million tokens.
Read this to understand how to build reliable corpus-scale agents with explicit evidence state, conclusion tracking, source provenance, revision semantics and targeted retrieval rather than relying on a growing chat transcript.
Songtao Huang, Zhijie Zhong, Xiaohan He
Read paper
GitSwarm
An asynchronous multi-agent system that uses a shared Git repository as persistent memory, enabling agents to reuse successful work and failed experiments across long-horizon tasks.
Read this to understand a practical architecture for persistent multi-agent collaboration, including Git worktrees, semantic dependency graphs, decentralized candidate selection, artifact reuse and the costs of scaling agent swarms.
Vedant Shah, Ankur Samanta, Paras Dahal
Read paper
StreamEval
An interactive streaming-video benchmark revealing the gap between visual quality and reliable real-time instruction following across avatars, world generation and video editing.
Read this to understand how to evaluate real-time multimodal products beyond frame quality: control following, state preservation, temporal continuity, audiovisual synchronization and long-horizon reliability.
StreamEval Team
Read paper
Gemini 4 Carbon
A technical reading of Gemini 4 Carbon: coding and agentic claims, security benchmarks, safety measures, availability, and what developers should verify.
AI engineers, security researchers, and engineering leaders evaluating long-horizon coding agents and AI-assisted security workflows.
Google DeepMind
Read paper
Mamba-3: Efficient State Space Models
Research deep dive into Mamba-3: recurrence, complex state updates, MIMO, benchmark results, official code, and engineering trade-offs.
ML engineers and researchers evaluating efficient recurrent architectures, long-context inference, and alternatives to Transformer attention.
Aakash Lahoti, Kevin Y. Li, Berlin Chen
Read paper
Nemotron Bolt E4B 4GB
Technical guide to NVIDIA's compact local-agent model: model lineage, quantization, benchmark interpretation, hardware measurements, tool-calling architecture, and practical deployment guidance.
Developers building local voice agents, interactive NPCs, or embedded AI systems who need to understand memory, latency, tool execution, and deployment trade-offs.
NVIDIA
Read paper
Ambient Quality Agent (AQuA)
A practical guide to production agent quality: trace sampling, multi-stage evaluation, root-cause clustering, code-aware investigation, and a continuous improvement loop.
Read this if you build multi-agent systems and need to detect semantic regressions that ordinary uptime and latency monitoring miss.
Google ADK Recipes contributors
Read paper
Reverse Engineer Anything: Practical Guide
A hands-on guide to REA with CLI/MCP commands, Python and TypeScript examples, a full feature-tracing lab, production runbooks, and evidence-based benchmark analysis.
Use this as a practical learning path: start with static analysis, run a focused investigation, build a replacement with differential tests, and learn where AI reverse-engineering agents still fail.
MachinoAI Research Desk
Read paper