Mindscape-Aware RAG (MiA-RAG) helps RAG systems handle long documents by first building a high-level summary of the whole text. This “global view” is then used to guide what the system retrieves and how it answers, helping it connect scattered evidence and reason more like a human reading a long document. → Read more

Multi-step RAG with Hypergraph-based Memory: HGMem is a new memory design that enhances multi-step RAG. It organizes retrieved information as a hypergraph, allowing facts to connect and combine over time. This helps the model build structured knowledge, reason more coherently, and better understand complex contexts. → Read more

QuCo-RAG is a dynamic RAG method that decides when to retrieve information based on statistics from the model’s pretraining data, not model confidence. It flags rare or suspicious entities and checks whether they co-occur in real data, triggering retrieval to reduce hallucinations and improve factual accuracy. → Read more

HiFi-RAG is a hierarchical RAG pipeline that filters retrieved documents in multiple stages before generation. It uses Gemini 2.5 Flash to reformulate queries, prune irrelevant passages, and attach citations, then relies on Gemini 2.5 Pro only for final answer generation. → Read more

Bidirectional RAG allows controlled write-back to the retrieval corpus. Generated answers are added only if they pass grounding checks, including NLI-based entailment, source attribution verification, and novelty detection. This lets the system expand its knowledge base during use without polluting it with hallucinations. → Read more

TV-RAG is a training-free RAG framework for long videos that adds time awareness to retrieval. It ranks retrieved text using temporal offsets and selects key video frames with entropy-based sampling, helping video language models align visual, audio, and subtitle information and reason more accurately over long video timelines. → Read more

MegaRAG is built around multimodal knowledge graphs for long documents like books. It extracts entities and relations from text and visuals, builds a hierarchical graph, and uses it during retrieval and generation. This helps the model reason globally and answer both text and visual questions more accurately. → Read more

AffordanceRAG is a zero-shot, multimodal RAG system for mobile robots. It builds an affordance-aware memory from images of explored environments, retrieves objects and locations using visual and regional features, and reranks them with affordance scores to select actions the robot can physically execute, improving real-world manipulations. → Read more

Graph-O1 is an agent-based GraphRAG system for question answering over text-attributed graphs. Instead of reading the whole graph at once, it uses Monte Carlo Tree Search (MCTS) and reinforcement learning (RL) to explore only the most relevant nodes and edges step by step, enabling efficient, structured reasoning within LLM context limits. → Read more

SignRAG is a zero-shot road sign recognition system built on RAG. It uses a vision–language model to describe a sign image, retrieves similar sign designs from a vector database, and then lets an LLM reason over the candidates to identify the correct sign, without task-specific training. → Read more

Hybrid RAG for Multilingual Document Question Answering is a multilingual RAG system for question answering over noisy historical newspapers. It handles OCR errors and language drift using semantic query expansion, multi-query retrieval with Reciprocal Rank Fusion, and a grounded generation prompt that only answers when evidence exists. → Read more

RAGPart and RAGMask are lightweight defenses against RAG corpus poisoning attacks. RAGPart limits the influence of malicious documents by exploiting how dense retrievers learn from partitioned data, and RAGMask flags suspicious documents by masking tokens and detecting abnormal similarity shifts, without modifying the generation model. → Read more