AURA-Mem uses an action-gated recurrent memory trained on closed-loop action error to deliver constant 4,224-byte state and 5-9x fewer writes than baselines while matching base policy success on LIBERO-Long.
hub
It’s all connected: A journey through test-time memorization, attentional bias, retention, and online optimization
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
WaveLiT combines wavelet tokenization, linear attention, and multiscale pyramids to produce parameter-efficient neural PDE solvers that match much larger models on TheWell benchmarks.
TIDE is a neuro-inspired architecture using stabilized asymmetric E-I networks with lateral inhibition and 80:20 balance that trains in under half the time of CTM while gaining +1.65% top-1 accuracy on perturbed ImageNet.
Scal3R achieves better accuracy and consistency in large-scale 3D scene reconstruction by maintaining a compressed global context through test-time adaptation of lightweight neural networks on long video sequences.
Elastic Test-Time Training stabilizes test-time updates via an elastic prior and moving-average anchor, enabling Fast Spatial Memory for scalable long-sequence 4D reconstruction with reduced memory use and fewer shortcuts.
In-Place TTT adapts LLM MLP projection matrices at test time with a next-token-aligned objective and chunk-wise updates, enabling better long-context performance as a drop-in enhancement.
MSA is an end-to-end trainable memory model using sparse attention and document-wise RoPE that scales to 100M tokens with linear complexity and less than 9% degradation.
Large-chunk online updates during inference let test-time training scale state capacity to 40% of model size and handle contexts up to 1M tokens without custom kernels.
Caracal is a Fourier-based sequence mixing architecture that achieves causal autoregressive modeling with standard operators and competitive performance on long sequences.
TTT3R derives a closed-form learning rate from memory-observation alignment confidence to boost length generalization in RNN-based 3D reconstruction by 2x in global pose estimation.
A distributed online convex optimization protocol for associative memory achieves sublinear regret guarantees and outperforms baselines in experiments.
Argues that parametric attention forms are necessary for lifelong in-context learning in transformers to maintain constant memory footprint over arbitrary sequence lengths.
citing papers explorer
-
AURA: Action-Gated Memory for Robot Policies at Constant VRAM
AURA-Mem uses an action-gated recurrent memory trained on closed-loop action error to deliver constant 4,224-byte state and 5-9x fewer writes than baselines while matching base policy success on LIBERO-Long.
-
Rethinking Memory as Continuously Evolving Connectivity
FluxMem evolves memory as a heterogeneous graph via three refinement stages and reports consistent state-of-the-art results on LoCoMo, Mind2Web, and GAIA benchmarks.
-
Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers
WaveLiT combines wavelet tokenization, linear attention, and multiscale pyramids to produce parameter-efficient neural PDE solvers that match much larger models on TheWell benchmarks.
-
TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics
TIDE is a neuro-inspired architecture using stabilized asymmetric E-I networks with lateral inhibition and 80:20 balance that trains in under half the time of CTM while gaining +1.65% top-1 accuracy on perturbed ImageNet.
-
Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction
Scal3R achieves better accuracy and consistency in large-scale 3D scene reconstruction by maintaining a compressed global context through test-time adaptation of lightweight neural networks on long video sequences.
-
Fast Spatial Memory with Elastic Test-Time Training
Elastic Test-Time Training stabilizes test-time updates via an elastic prior and moving-average anchor, enabling Fast Spatial Memory for scalable long-sequence 4D reconstruction with reduced memory use and fewer shortcuts.
-
In-Place Test-Time Training
In-Place TTT adapts LLM MLP projection matrices at test time with a next-token-aligned objective and chunk-wise updates, enabling better long-context performance as a drop-in enhancement.
-
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens
MSA is an end-to-end trainable memory model using sparse attention and document-wise RoPE that scales to 100M tokens with linear complexity and less than 9% degradation.
-
Test-Time Training Done Right
Large-chunk online updates during inference let test-time training scale state capacity to 40% of model size and handle contexts up to 1M tokens without custom kernels.
-
Caracal: Causal Architecture via Spectral Mixing
Caracal is a Fourier-based sequence mixing architecture that achieves causal autoregressive modeling with standard operators and competitive performance on long sequences.
-
TTT3R: 3D Reconstruction as Test-Time Training
TTT3R derives a closed-form learning rate from memory-observation alignment confidence to boost length generalization in RNN-based 3D reconstruction by 2x in global pose estimation.
-
Distributed Associative Memory via Online Convex Optimization
A distributed online convex optimization protocol for associative memory achieves sublinear regret guarantees and outperforms baselines in experiments.
-
Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention
Argues that parametric attention forms are necessary for lifelong in-context learning in transformers to maintain constant memory footprint over arbitrary sequence lengths.