GAIA introduces a geometry-adaptive integral autoencoder that unifies forward, boundary-value, and inverse PDE operator learning on arbitrary domains via geometry tokens and cross-attention.
hub
Transformers are rnns: Fast autoregressive transformers with linear attention
13 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
13
Pith papers citing it
2
external citations · OpenAlex
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
MEEC equips point clouds with a discrete exterior calculus that satisfies exact conservation and is differentiable in point positions, allowing a single trained kernel to produce compatible physics on unseen geometries and parameters.
EQ-VMamba adds rotation-equivariant cross-scan and group Mamba blocks to enforce end-to-end rotation equivariance, yielding better rotation robustness, competitive accuracy, and roughly 50% fewer parameters than non-equivariant baselines across classification, segmentation, and super-resolution.
Mamba-VGGT introduces a Sliding Window Mamba memory module and Zero-Init Spatial Memory Injector to enable persistent long-range geometric reasoning in VGGT for extended video sequences.
Stream-CQSA uses CQS-based decomposition to stream exact attention computations for billion-token sequences on limited-memory hardware.
HormoneT5 augments T5 with a hormone-inspired block that predicts six continuous emotion values and uses them to modulate responses, reporting over 85% per-hormone accuracy and human preference for emotional quality.
The Inverter framework formalizes inverse learning to generate coherent multi-step trajectories, outperforming offline RL and diffusion baselines on D4RL maze tasks by 24% on average with 10-100x less inference time while also matching GRAPE fidelity on single-qubit gates at >1000x speed.
Training transformers with KV sparsification during continued pretraining produces representations that admit better post-hoc KV cache compression, improving quality under memory budgets for long-context tasks.
Dynamic parameterization of standard layers can replace explicit attention for linear-time global visual modeling.
UniBCI is a unified pretrained model for invasive neural spike data that uses CST tokenization, IAA attention, and self-supervised masked reconstruction to achieve SOTA downstream performance with better generalization and efficiency.
Authors introduce the Pursuit of Subspaces (PoS) hypothesis, an axiomatic geometric framework that unifies explanations for representation, computation, and generalization in shallow and deep neural networks.
SANA-WM is a 2.6B-parameter efficient world model that synthesizes minute-scale 720p videos with 6-DoF camera control, trained on 213K public clips in 15 days on 64 H100s and runnable on single GPUs at 36x higher throughput than prior open baselines.
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.
citing papers explorer
-
GAIA: Geometry-Adaptive Operator Learning for Forward and Inverse Problems
GAIA introduces a geometry-adaptive integral autoencoder that unifies forward, boundary-value, and inverse PDE operator learning on arbitrary domains via geometry tokens and cross-attention.
-
A meshfree exterior calculus for generalizable and data-efficient learning of physics from point clouds
MEEC equips point clouds with a discrete exterior calculus that satisfies exact conservation and is differentiable in point positions, allowing a single trained kernel to produce compatible physics on unseen geometries and parameters.
-
Rotation Equivariant Mamba for Vision Tasks
EQ-VMamba adds rotation-equivariant cross-scan and group Mamba blocks to enforce end-to-end rotation equivariance, yielding better rotation robustness, competitive accuracy, and roughly 50% fewer parameters than non-equivariant baselines across classification, segmentation, and super-resolution.
-
Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory
Mamba-VGGT introduces a Sliding Window Mamba memory module and Zero-Init Spatial Memory Injector to enable persistent long-range geometric reasoning in VGGT for extended video sequences.
-
Stream-CQSA: Avoiding Out-of-Memory in Attention Computation via Flexible Workload Scheduling
Stream-CQSA uses CQS-based decomposition to stream exact attention computations for billion-token sequences on limited-memory hardware.
-
A Hormone-inspired Emotion Layer for Transformer language models (HELT)
HormoneT5 augments T5 with a hormone-inspired block that predicts six continuous emotion values and uses them to modulate responses, reporting over 85% per-hormone accuracy and human preference for emotional quality.
-
Neuro-Inspired Inverse Learning for Planning and Control
The Inverter framework formalizes inverse learning to generate coherent multi-step trajectories, outperforming offline RL and diffusion baselines on D4RL maze tasks by 24% on average with 10-100x less inference time while also matching GRAPE fidelity on single-qubit gates at >1000x speed.
-
Training Transformers for KV Cache Compressibility
Training transformers with KV sparsification during continued pretraining produces representations that admit better post-hoc KV cache compression, improving quality under memory budgets for long-context tasks.
-
Linear-Time Global Visual Modeling without Explicit Attention
Dynamic parameterization of standard layers can replace explicit attention for linear-time global visual modeling.
-
UniBCI: Towards a Unified Pretrained Model for Invasive Brain-Computer Interfaces
UniBCI is a unified pretrained model for invasive neural spike data that uses CST tokenization, IAA attention, and self-supervised masked reconstruction to achieve SOTA downstream performance with better generalization and efficiency.
-
Axiomatizing Neural Networks via Pursuit of Subspaces
Authors introduce the Pursuit of Subspaces (PoS) hypothesis, an axiomatic geometric framework that unifies explanations for representation, computation, and generalization in shallow and deep neural networks.
-
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
SANA-WM is a 2.6B-parameter efficient world model that synthesizes minute-scale 720p videos with 6-DoF camera control, trained on 213K public clips in 15 days on 64 H100s and runnable on single GPUs at 36x higher throughput than prior open baselines.
-
Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism
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.