Bridging Distance and Spectral Positional Encodings via Anchor-Based Diffusion Geometry Approximation (2026.acl-long)
Copied to clipboard
| Challenge: | Molecular graph learning benefits from positional signals that capture local neighborhoods and global topology. |
| Approach: | They propose to use anchor-based distance encodings to approximate diffusion geometry. |
| Outcome: | The proposed model outperforms models without positional encodings on DrugBank with a shared GNP-based DDI backbone. |
Similar Papers
Randomized Positional Encodings Boost Length Generalization of Transformers (2023.acl-short)
Copied to clipboard
Anian Ruoss, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Róbert Csordás, Mehdi Bennani, Shane Legg, Joel Veness
| Challenge: | Moreover, simply training on longer sequences is inefficient due to the quadratic computation complexity of the global attention mechanism. |
| Approach: | They propose a randomized positional encoding scheme that randomly selects an ordered subset to fit the sequence’s length. |
| Outcome: | The proposed method allows Transformers to generalize to sequences of unseen length (increasing test accuracy by 12.0% on average). |
Towards Dynamic Computation Graphs via Sparse Latent Structure (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to learn latent structure are limited by factorization assumptions or end-to-end differentiability. |
| Approach: | They propose a method that allows for end-to-end learning of latent structure predictors jointly with a downstream predictor. |
| Outcome: | The proposed method allows for unrestricted dynamic graph construction from the global latent structure while maintaining differentiability. |
GeoLAN: Geometric Learning of Latent Explanatory Directions in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models lack transparency and are often unable to explain causal relationships . |
| Approach: | They propose a training framework that treats token representations as geometric trajectories and applies stickiness conditions to the Kakeya Conjecture. |
| Outcome: | The proposed training framework maintains task accuracy while improving geometric metrics and reducing fairness biases. |
Mitigating Tokenization-Induced Distance Distortion in Long-Context Multilingual Machine Translation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing positional encodings rely on fixed token indices and implicitly assume uniform semantic density, which breaks down for long-context inputs. |
| Approach: | They propose a tokenization-aware adaptive positional encoding that conditions relative positional bias on input-level sequence length and fragmentation statistics. |
| Outcome: | The proposed model improves long-context robustness and accuracy over baselines. |
Label-Agnostic Sequence Labeling by Copying Nearest Neighbors (P19-1)
Copied to clipboard
| Challenge: | Retrieve-and-edit based structured prediction models condition on retrieved neighbors to generate new structures, but many models do not explicitly capture the discrete operations that allow for the neighbors to be edited into the target structure. |
| Approach: | They propose to explicitly condition on retrieved neighbors to create new structures . they propose to use a dynamic programming approach to sequence labeling . |
| Outcome: | The proposed model can perform accurate sequence labeling by explicitly copying labels from retrieved neighbors. |
Exact yet Efficient Graph Parsing, Bi-directional Locality and the Constructivist Hypothesis (2020.acl-main)
Copied to clipboard
| Challenge: | Existing algorithms for graph parsing are exponential or high-degree polynomial w.r.t. grammars, and there are few systems that can parse large but frequent MRs with a realistic, wide-coverage grammar in a reasonable time. |
| Approach: | They propose an exact graph parsing algorithm that exploits locality as terminal edge-adjacency in HRG rules and categorizes a subclass of HRG. |
| Outcome: | The proposed method can parse graphs with a (competence) grammar in a time-efficient manner. |
Data-to-text Generation by Splicing Together Nearest Neighbors (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on data-to-text generation relies on retrieved "neighbors" but instead generates text token-by-token, left-to right. |
| Approach: | They propose to splice together retrieved segments of text from "neighbor" source-target pairs to generate text token-by-token, left-to-right. |
| Outcome: | The proposed method performs on par with strong baselines in terms of automatic and human evaluation, but allows for more interpretable and controllable generation. |
Hierarchical Bracketing Encodings Work for Dependency Graphs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Sequence labeling (SL) is a simple yet effective paradigm for a wide range of natural language problems. |
| Approach: | They propose a new bracketing approach for dependency graph parsing that encodes graphs as sequences and n tagging actions. |
| Outcome: | The proposed approach significantly reduces label space while preserving structural information. |
Compressing LLM Knowledge into Graph Representations for Text-attributed Graphs Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing GNN-LLM approaches use large language models at inference time for processing text attributes, resulting in costly deployment. |
| Approach: | They propose a framework that internalizes LLM knowledge within graph models and supports inference-efficient TAG learning. |
| Outcome: | The proposed framework internalizes LLM knowledge within graph models and supports inference-efficient TAG learning. |
SCOPE: Boosting LLM Efficiency with Scoped Position Encoding (2026.acl-long)
Copied to clipboard
| Challenge: | Positional encodings are fundamental to Transformers, but explicit methods like RoPE can degrade under length extrapolation and incur extra arithmetic and memory-access overhead. |
| Approach: | They propose a framework that reimagines structured sparsity as an intrinsic position encoding mechanism. |
| Outcome: | The proposed framework reduces the number of attention FLOPs by 8x compared to RoPE on LLaMA-3-8B architectures while reducing training and inference latency. |