Reconstruction-based IMVC is structurally untrainable when complete-sample proportion falls near zero; CRAFT escapes that bound via per-sample attention-masked fusion trained once on complete data.
hub Canonical reference
Perceiver: General perception with iterative attention
Canonical reference. 80% of citing Pith papers cite this work as background.
15
Pith papers citing it
128
external citations · external index
Background
80% of classified citations
hub tools
citation-role summary
background 4
method 1
citation-polarity summary
representative citing papers
Bottleneck Tokens paired with a masked generative objective achieve state-of-the-art unified multimodal retrieval performance among 2B-scale models on the MMEB-V2 benchmark with 78 datasets.
LGS pretrained on 2.5M trajectories across 16 systems matches deterministic baselines at one step and halves 20-step error while using far less compute and adapting to held-out higher-resolution flows.
Chronos elevates full observation history to the policy's latent state via selective SSM tokens and a Schrödinger-inspired acceleration bridge, achieving large gains on memory-dependent robot tasks with fewer parameters.
MetaRL pre-trained on GBWM problems delivers near-optimal dynamic strategies in 0.01s achieving 97.8% of DP optimal utility and handles larger problems where DP fails.
Knowledge conflicts in hypernetwork LLM adaptation stem from constant adapter margins losing to frequency-dependent pretrained margins; selective layer boosting and conflict-aware triggering raise deep-conflict accuracy to 71-72.5% on Gemma-2B and Mistral-7B.
HubRouter is a sub-quadratic routing primitive using learned hubs that replaces attention layers in hybrid models while delivering competitive perplexity and large throughput gains.
GAF creates 4D dynamic scene models by adding motion to 3D Gaussians, enabling better reconstruction and 7.3% higher success in robotic tasks.
Aurora's latent space is organized by seasonal cycles with evidence of encoding 3D vertical atmospheric structure for storms, confirmed by perturbation experiments.
MLT-Dedup achieves 91% reduction in online video repetition rates at 90% precision and 5x indexing capacity using multi-level representations and differential feature-enhanced similarity on a real-world platform.
CART is a recurrent transformer with shared core, frozen prelude KV tensors, and LTI stability gate that fails to beat dense baselines at parameter parity across tested widths.
StereoPolicy fuses left-right image features via cross-attention to deliver consistent gains over RGB, RGB-D, point cloud, and multi-view baselines in simulation and real-robot manipulation tasks.
citing papers explorer
-
Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC
Reconstruction-based IMVC is structurally untrainable when complete-sample proportion falls near zero; CRAFT escapes that bound via per-sample attention-masked fusion trained once on complete data.
-
Bottleneck Tokens for Unified Multimodal Retrieval
Bottleneck Tokens paired with a masked generative objective achieve state-of-the-art unified multimodal retrieval performance among 2B-scale models on the MMEB-V2 benchmark with 78 datasets.
-
Latent Generative Solvers for Generalizable Long-Term Physics Simulation
LGS pretrained on 2.5M trajectories across 16 systems matches deterministic baselines at one step and halves 20-step error while using far less compute and adapting to held-out higher-resolution flows.
-
Chronos: A Physics-Informed Full-History Framework for Non-Markovian Long-Horizon Manipulation
Chronos elevates full observation history to the policy's latent state via selective SSM tokens and a Schrödinger-inspired acceleration bridge, achieving large gains on memory-dependent robot tasks with fewer parameters.
-
A Meta Reinforcement Learning Approach to Goals-Based Wealth Management
MetaRL pre-trained on GBWM problems delivers near-optimal dynamic strategies in 0.01s achieving 97.8% of DP optimal utility and handles larger problems where DP fails.
-
The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
Knowledge conflicts in hypernetwork LLM adaptation stem from constant adapter margins losing to frequency-dependent pretrained margins; selective layer boosting and conflict-aware triggering raise deep-conflict accuracy to 71-72.5% on Gemma-2B and Mistral-7B.
-
HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models
HubRouter is a sub-quadratic routing primitive using learned hubs that replaces attention layers in hybrid models while delivering competitive perplexity and large throughput gains.
-
GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation
GAF creates 4D dynamic scene models by adding motion to 3D Gaussians, enabling better reconstruction and 7.3% higher success in robotic tasks.
-
Does Aurora Encode Atmospheric Structure? Latent Regime Analysis and Attribution
Aurora's latent space is organized by seasonal cycles with evidence of encoding 3D vertical atmospheric structure for storms, confirmed by perturbation experiments.
-
MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representations and Spatial-Temporal Matching
MLT-Dedup achieves 91% reduction in online video repetition rates at 90% precision and 5x indexing capacity using multi-level representations and differential feature-enhanced similarity on a real-world platform.
-
CART: Context-Anchored Recurrent Transformer -- A Parameter-Efficient Architecture with Learned Stability
CART is a recurrent transformer with shared core, frozen prelude KV tensors, and LTI stability gate that fails to beat dense baselines at parameter parity across tested widths.
-
StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception
StereoPolicy fuses left-right image features via cross-attention to deliver consistent gains over RGB, RGB-D, point cloud, and multi-view baselines in simulation and real-robot manipulation tasks.
- Domain-Gated Latent Diffusion: Generative Inverse Design of HMX-Class Energetic Materials with First-Principles Validation
- Enhancing event reconstruction for $\gamma$-ray particle detector arrays using transformers
- A Self-Supervised Framework for Space Object Behaviour Characterisation