memory-augmentation

Tag

Cards List
#memory-augmentation

RecurTrace: Adaptive Latent Reasoning with Loop-Time Memory

arXiv cs.LG · 5d ago Cached

RecurTrace introduces loop-time memory and adaptive halting to improve latent reasoning in language models, achieving higher accuracy on MathQA with optimized compute compared to fixed-loop methods.

0 favorites 0 likes
#memory-augmentation

Decoupled Analysis-Judging: An Automated Creativity Evaluator Using LLMs in Complex Multi-step Creativity Tasks

arXiv cs.CL · 5d ago Cached

This paper introduces CreaEval, an automated creativity evaluator for complex multi-step tasks that decouples analysis and judging to reduce biases and improve evaluation reliability, demonstrating a 22.74% average performance improvement over baselines.

0 favorites 0 likes
#memory-augmentation

@rsasaki0109: PriorEye: Geospatial Visual Priors for End-to-End Autonomous Driving ECCV 2026 https://github.com/ori-mrg/PriorEye… Mos…

X AI KOLs Timeline · 2026-08-23 Cached

PriorEye introduces geospatial visual priors for end-to-end autonomous driving, enhancing anticipatory behavior and robustness through a dual-memory architecture, as presented at ECCV 2026.

0 favorites 0 likes
#memory-augmentation

Speculate with Memory: Lossless Acceleration for LLM Agents

arXiv cs.LG · 2026-07-15 Cached

This paper introduces memory-augmented speculative execution for LLM agents, using three online memory systems to improve prediction accuracy by 19-39% on action prediction and up to 2.5x on observation prediction, all while being lossless with zero added wall-clock cost.

0 favorites 0 likes
#memory-augmentation

TF-Engram: A Train-Free Engram with SSD-Backed Memory for Large Language Models

arXiv cs.CL · 2026-07-09 Cached

TF-Engram introduces a train-free system that stores phrase-level semantic memory on a GPU-DRAM-SSD hierarchy for LLMs, using predictive prefetching to hide latency, and demonstrates improved downstream performance on Qwen3-0.6B.

0 favorites 0 likes
#memory-augmentation

MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation

arXiv cs.AI · 2026-06-11 Cached

This paper introduces MA-DLE, a memory-based feature augmentation method for speech-based automatic depression level estimation, achieving state-of-the-art performance on the DAIC-WOZ and E-DAIC datasets.

0 favorites 0 likes
#memory-augmentation

Latent Preference Modeling for Cross-Session Personalized Tool Calling

Hugging Face Daily Papers · 2026-04-20 Cached

Introduces MPT benchmark and PRefine method for cross-session personalized tool calling that captures user choice reasoning with minimal token overhead.

0 favorites 0 likes
← Back to home

Submit Feedback