Papers

A research paper that detects AI-generated commercial blog content from structural signatures alone, such as ordering and evidence, rather than wording, reaching 98 macro-F1 and identifying which model wrote it.

• Papers

A structured, decision-grade evidence base on long-term memory for LLM agents, combining a 989-paper index, archived source pages, product notes, benchmark protocols and architecture maps.

• Papers

A research paper and accompanying code that stores a user's facts as a few rows in a content-addressed edit to a language model's parameters, instead of a separate retrieval index or per-user LoRA.

• Agent memory
• Papers

A continuously updated survey that collects and verifies public demonstrations of frontier multimodal models doing 3D modeling, computational design and robotics work, assessing what they can reliably do today.

• Papers

A curated reading list of research on models and agents that improve reasoning and planning by iteratively refining an internal latent state rather than producing explicit intermediate text, spanning supervised reasoners and reinforcement-learned planning.

• Curated lists
• Papers

Research code for a system that answers open-ended questions about artworks by having a multimodal LLM read a painting and a predicted artwork card, then retrieving supporting passages from a multimodal Wikipedia knowledge base when it needs external knowledge.

• RAG
• Papers

A small transformer variant that merges the attention layer with the SwiGLU feed-forward layer to cut parameters at very small model sizes, without losing much performance.

• Models
• Papers

The official implementation of a CVPR 2025 paper on retrieval-augmented neural fields for embedding geographic coordinates, with a pip-installable package that returns high-resolution visual-feature embeddings for any latitude and longitude.

• Models
• Papers

Research code and results accompanying a paper showing that a transformer's KV cache can be edited in place or recombined across contexts instead of always being recomputed, with large throughput and latency gains.

• Papers

A mechanistic-interpretability research project testing whether a language model's internal activations can reveal the operation and operands of an arithmetic prompt well enough to route it to a calculator without parsing the prompt text.

• Papers

Research code for a Blackwell-GPU LLM inference method that combines a sparse FP4 main computation path with a dense FP4 residual path to recover accuracy lost to sparsification and quantization, with a PyTorch-only simulation mode for accuracy testing without the CUDA kernel.

• Inference
• Papers

An independent structural validation report on two split GGUF releases of the Kimi K3 model, checking descriptor counts, identities, and shapes between quantization variants without downloading any tensor payload bytes.

• Models
• Papers

A post-training quantization method, presented at ICML 2026, that compresses large language model weights below one bit per parameter using mixture-of-rank binary bases while preserving accuracy.

• Models
• Papers

A mechanistic interpretability study tracking whether the induction-head circuit in a small attention-only transformer survives fine-tuning from prose to structured Python code, using per-head induction scores and activation patching across training checkpoints.

• Papers

A research playground that guides an Isabelle/HOL theorem prover with large language models, combining LLM-proposed tactics with Isabelle's own nitpick, quickcheck, and sledgehammer, and a beam search over proof outlines.

• Papers

The official implementation of a CIKM 2024 paper that improves multimodal electronic health record prediction with retrieval-augmented summaries from a knowledge graph.

• RAG
• Papers

Research code for a knowledge-graph-based RAG method that retrieves relevant subgraphs from large external knowledge graphs to augment LLM prompts for the schema-matching and data-integration task.

• RAG
• Papers

A research framework, published at ICLR'26, that decomposes multi-hop questions into a query subgraph and traverses a graph of document chunks to retrieve reasoning-aligned context for RAG at a fraction of the LLM cost of prior methods.

• RAG
• Papers

A curated collection of research papers on GUI agent safety, organized by environment and keyword, covering benchmarks, datasets, attacks, defenses and evaluation frameworks for computer-use and mobile or desktop agents.

• AI evals
• Security
• Papers

A research inference engine that proves a full transformer forward pass can run through a single algebraic operation, exponentiation combined with a logarithm and subtraction, in place of ordinary multiplication.

• Inference
• Papers

A research training method and codebase where a student model learns from a teacher's demonstrations while a constraint limits how far it can drift, aimed at fine-tuning a model on a new task without forgetting old ones.

• Models
• Papers

Research code that reproduces the experiments behind the paper 'MLPs are Hebbians: Constructing Efficient Fact-Storing MLPs for Transformers', including Hebbian MLP construction, Transformer integration and fact-editing experiments.

• Models
• Papers

A retrieval-augmented generation framework built on the HippoRAG 2 architecture that turns a static knowledge graph into a query-adaptive navigation structure, reproduced with the prompts and dataset from its ACL 2026 paper.

• RAG
• Papers

ArxivExplorer is a semantic search engine for arXiv papers that combines keyword and vector search, generates AI summaries and entity extraction for each paper, and tracks citations, without requiring a login.

• RAG
• Papers