REALM augments language-model pre-training with an unsupervised retriever over Wikipedia documents and reports 4-16% absolute gains on open-domain QA benchmarks over prior implicit and explicit knowledge methods.
hub
Gener- alization through memorization: Nearest neighbor language models.ArXiv, abs/1911.00172
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
AR-VLA introduces a standalone autoregressive action expert with long-lived memory that generates context-aware continuous actions for VLAs, replacing chunk-based heads with smoother trajectories and maintained task success.
NeuroKalman mitigates state drift in vision-language UAV navigation by using memory-augmented Kalman filtering where attention retrieves historical anchors to correct predictions without gradient updates.
LLaMA-Adapter turns frozen LLaMA 7B into a capable instruction follower using only 1.2M new parameters and zero-init attention, matching Alpaca while extending to image-conditioned reasoning on ScienceQA and COCO.
Intra-layer model parallelism in PyTorch enables training of 8.3B-parameter transformers, achieving SOTA perplexity of 10.8 on WikiText103 and 66.5% accuracy on LAMBADA.
A hybrid attention mechanism with editable request-local memory slots and sparse fallback achieves high accuracy on synthetic overwrite, version, and anti-pollution tasks where pure fixed-state or sparse methods fail, while identifying open-domain selection as the remaining bottleneck.
Tensor Memory augments Transformers with a constant-size 3D voxel grid using differentiable soft writes at predicted locations, local interaction, and gated recurrent dynamics to decouple memory capacity from sequence length.
FedRAG uses a Scrambled Distributed Attention protocol with feature scrambling and token permutation to enable high-throughput, privacy-preserving federated RAG without special hardware or retraining.
SegRAG is a training-free retrieval-augmented framework that extracts class-specific point prompts from a filtered DINOv3 feature bank to boost SAM3 semantic segmentation performance on standard and agricultural benchmarks.
Memory Inception is a training-free method that injects latent KV banks at chosen layers to steer LLMs, achieving superior control-drift balance and up to 118x storage reduction on personality and structured-reasoning tasks.
A context-aware Sentinel-Strategist system for RAG selectively applies defenses to block membership inference and data poisoning while recovering most retrieval utility compared to always-on defense stacks.
Loss-based pruning of training data to limit facts and flatten their frequency distribution enables a 110M-parameter GPT-2 model to memorize 1.3 times more entity facts than standard training, matching a 1.3B-parameter model on the full dataset.
AtlasKV integrates billion-scale KGs into LLMs parametrically with sub-linear complexity and low memory by converting triples into key-value representations handled by the model's attention.
RAPTOR introduces a tree-organized retrieval method using recursive abstractive summaries, achieving a 20% absolute accuracy improvement on the QuALITY benchmark when paired with GPT-4.
MetaCLIP curates balanced 400M-pair subsets from CommonCrawl that outperform CLIP data, reaching 70.8% zero-shot ImageNet accuracy on ViT-B versus CLIP's 68.3%.
LaMDA shows that fine-tuning on human-value annotations and consulting external knowledge sources significantly improves safety and factual grounding in large dialog models beyond what scaling alone achieves.
NGM is a plug-and-play n-gram memory module that encodes n-grams from pretrained embeddings and gates their injection to improve LLM performance by 0.5-1.2 points on average across eight benchmarks.
TIDE augments standard transformers with per-layer token embedding injection via an ensemble of memory blocks and a depth-conditioned router to mitigate rare-token undertraining and contextual collapse.
FAAST performs test-time supervised adaptation by analytically deriving fast weights from examples in one forward pass, matching backprop performance with over 90% less adaptation time and up to 95% memory savings versus memory-based methods.
HoReN is a parameter-preserving editor that wraps an MLP with a Hopfield codebook memory and scales to 50K sequential edits on ZsRE while maintaining performance above 0.93.
Nirvana adds a task-aware memory trigger and updater to specialized generalist models, achieving strong general benchmark results, lowest perplexity in biomedicine/finance/law, and improved MRI reconstruction fidelity.
RAG-enhanced LLMs show generally positive effects on automated test generation and code inspection by supplying supplementary context that reduces hallucinations.
citing papers explorer
-
NGM: A Plug-and-Play Training-Free Memory Module for LLMs
NGM is a plug-and-play n-gram memory module that encodes n-grams from pretrained embeddings and gates their injection to improve LLM performance by 0.5-1.2 points on average across eight benchmarks.