Causal Attention

Follow this topic Ask about this topic

Recent momentum

-73%

3 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

1 new paper

A weekly snapshot of new work published in Causal Attention.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Causal Attention.

Period ending 2026-09-07

5 new papers

A weekly snapshot of new work published in Causal Attention.

77 papers

Latest in Causal Attention

Open your feed →

MaSCoD: A Multi-Agent Framework for Structural-Context-Guided Candidate Causal Graph Generation
Sep 17, 2026Yudai Nakada, Yuichiro Nishiura, Jin Michael SplichalCausal Graph Reasoning Graphs
CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling
Sep 8, 2026Xinran Duan, Guozhang Li, Yaoyao Zhong +3Video Understanding Video Captioning
Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment
Sep 1, 2026Mian Zhong, Katherine A. Keith, Anjalie FieldImproving Sparse Autoencoders Latent Confounders
TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning
Aug 12, 2026Shuangqing Zhang, Lei-Lei Ma, Zhao Wang +5Video Anomaly Understanding Fine-Grained Video Understanding
Causal Structure is Inducible but Functionally Decoupled: The Routing/Readout Boundary of a Typed Mechanism Library
Aug 12, 2026Xining XunCausal Reasoning Causal Attention
Why Post-Norm Transformers Collapse: Attention Amplification and Gradient Repair Failure
Aug 10, 2026Xingjian Wang, Qingyu Han, Xiaodong Luo +1Batch Normalization Transformer Encoder
Scaling Inherently Interpretable Language Models
Aug 6, 2026Guide Labs Team, Andreas Madsen, Aya Abdelsalam Ismail +7Model Interpretability Training Language Models
Abstract Event Causal Rules: Induction and Application
Aug 5, 2026Ziwei Zheng, Peiqiong Chen, Bang WangCausal Attention
Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling
Aug 4, 2026Nathan Labiosa, David Buff, Ena Nayak +1Model Activations Causal Attention
DeltaFlow: Noise-Adaptive Bidirectional Gated Delta Networks for Embedded Language Flows
Aug 2, 2026Guangfu Guo, Xiaoqian Lu, Linsey Pang +4Diffusion Language Models Causal Attention
Causal Discovery with Inverted Self-attention for Multivariate Time Series
Jul 30, 2026Yusen Liu, Yong Wang, Yifan Yin +3Causal Foundation Models Time Series
Back from the Future: Key-Value Cache Management by Counter-Causal Surprise
Jul 30, 2026Stephen Gould, Anton van den HengelKey-Value Cache Cache
The Confounder Trap: Treatment-Encoding Representations in Causal Inference with Text
Jul 28, 2026Marie Neubrander, Graham Tierney, Alexander VolfovskyLatent Confounders Causal Inferences
PreDiff-LM: Pretrained Discrete Masked Diffusion Language Modeling with Hybrid Attention
Jul 28, 2026Zhengtao Yao, Runhao Li, Xupeng Chen +12Diffusion Language Models Large Language Model Pretraining
CAPT: A Multi-task Continuous Autoregressive Transformer enabling Cross-dataset and Cross-species Transfer for Calcium Population Dynamics
Jul 25, 2026Xinhong Xu, Yimeng Zhang, Yuanlong ZhangAutoregressive Transformers Causal Attention
Learning What Matters: Supervising Global Context Pruning with Causal Evidence Sets
Jul 23, 2026James E. AllchinCausal Attention Pruning
Encoding Invisible Causation for Bridge Diagnostic Agents: Triple-Guided Retrieval-Augmented Fine-Tuning with QLoRA
Jul 23, 2026Takato YasunoCausal Reasoning Causal Attention
Patch Policy: Efficient Embodied Control via Dense Visual Representations
Jul 20, 2026Gaoyue Zhou, Zichen Jeff Cui, Ada Langford +3Robot Policies Vision Transformer
Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models
Jul 17, 2026Andy Catruna, Emilian RadoiDiffusion Language Models Masked Diffusion Language Models
WanToFight: Real-Time Generative Game Engine for Multi-Player Combat Interaction
Jul 14, 2026Li Hu, Guangyuan Wang, Peng Zhang +1Motion Generation War
DAG-FM: A Foundation Model for Causal Discovery under Heterogeneous Causal Mechanisms
Jul 13, 2026Yikang Chen, Zhengkang Guan, Haoyuan Qian +3Causal Foundation Models Structural Causal Model
The Key to Going Linear: Analysis-Driven Transformer Linearization
Jul 8, 2026Anna Kuzina, Paul N. Whatmough, Babak Ehteshami BejnordiTransformer Architectures Causal Attention
A Unified Framework for In-Context Learning with Causal and Masked Language Models
Jul 5, 2026Chenrui Liu, Chuanlong Xie, Falong Tan +2In-Context Learning Causal Attention
Spec-AUF: Accept-Until-Fail Training under Train-Inference Misalignment for Masked Block Drafters
Jul 2, 2026Tianjian Yang, Meng LiDrafter Speculative Decoding
PARTREP: Learning What to Repeat for Decoder-only LLMs
Jul 2, 2026Andikawati P Widjaja, Yongjun Kim, Hyounghun Kim +1Large Language Model Decoder Repetition
HSAP: A Hierarchical Sequence-aware Parallelism for Hybrid-Context Generative Models
Jun 29, 2026Songxin Zhang, Zejian Xie, Zhuoyang Song +4Parallel Sequence Modeling
AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation
Jun 22, 2026Huadai Liu, Kaicheng Luo, Wen Wang +4Audio Latent Audio
Towards Error-Free Long Video Generation
Jun 21, 2026Shuning Chang, Weihua Chen, Jiasheng Tang +8Controllable Video Generation Causal Attention
Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead
Jun 20, 2026Muyang Du, Jason Roche, Junjie LaiZero-Shot Text-To-Speech Causal Attention
Local Causal Attribution of Chain-of-Thought Reasoning
Jun 20, 2026Dennis Wei, Yannis Belkhiter, Erik Miehling +1Efficient Chain-Of-Thought Reasoning Chain-of-Thought Reasoning
Causal Variational Deep Embedding: A Family of Interventional Generators for Confounded Images
Jun 19, 2026Jingyuan Chen, Kangrui Ruan, Junzhe ZhangVariational Autoencoder Latent Confounders
DCD-PFN: A Decoupling-Aware Foundation Model for Causal Discovery
Jun 19, 2026Zhengkang Guan, Yikang Chen, Yi He +5Causal Foundation Models Causal Graph
Revisiting Structural Dependency in Autoregressive Multi-Task Table Recognition via Order-Independent Cell-Level Representations
Jun 16, 2026Takaya KawakatsuTabular Learning Multi--Task Learning
FoundCause: Causal Discovery with Latent Confounders from Observational Data
Jun 16, 2026Patrick Blöbaum, Krishnakumar Balasubramanian, Shiva Prasad KasiviswanathanCausal Foundation Models Structural Causal Model
Gaze Heads: How VLMs Look at What They Describe
Jun 12, 2026Rohit Gandikota, David BauCausal Attention Narratives
Causal Object-Centric Models for Planning with Monte Carlo Tree Search
Jun 12, 2026Rodion Vakhitov, Leonid Ugadiarov, Alexey Skrynnik +1Monte Carlo Tree Search Object-Centric Learning
MiniPIC: Flexible Position-Independent Caching in <100LOC
Jun 11, 2026Nathan Ordonez, Thomas ParnellPrefill Cache
CausalMoE: A Billion-Scale Multimodal Foundation Model for Granger Causal Discovery with Pattern-Routed Heterogeneous Experts
Jun 11, 2026Bo Liu, Di Dai, Jingwei Liu +5Causal Foundation Models Causal Graph
Express Language Modeling
Jun 9, 2026Albert Gong, Annabelle Michael Carrell, Raaz Dwivedi +1Graph Language Models Causal Attention
Parallel Causal Associative Fields: Gated Sparse Memory for Long-Context Language Modeling
Jun 9, 2026Muhammad AhmedCausal Attention Efficient Long-Context Inference
Hasse Diagrams for Attention: A Partial Order Framework for Designing Transformer Masks
Jun 8, 2026Chentao Li, Han GuoTransformer Attention Causal Attention
OmniGen-AR: AutoRegressive Any-to-Image Generation
Jun 8, 2026Junke Wang, Xun Wang, Qiushan Guo +4Autoregressive Image Generation Visual Generation
Where does Absolute Position come from in decoder-only Transformers?
Jun 4, 2026Valeria Ruscio, Umberto Nanni, Fabrizio SilvestriTransformer Encoder Rotary Position Embedding
Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models
Jun 2, 2026Yuetian Lu, Ali Modarressi, Yihong Liu +1Mixture-Of-Expert Language Models Mixture-of-Experts Models
Learning Temporal Causal Structure via Smooth Differentiable Optimization
Jun 2, 2026Tong Zhao, Ce Guo, Wayne Luk +2Causal Foundation Models Temporal Dependence
TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery
May 29, 2026Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang +1Causal Foundation Models Causal Reasoning
Test Time Training for Supervised Causal Learning
May 28, 2026Zizhen Deng, Jiaru Zhang, Rui Ding +5Causal Foundation Models Supervised Learning
Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding
May 28, 2026Jianuo Huang, Yaojie Zhang, Qituan Zhang +3Speculative Decoding Causal Attention
Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models
May 28, 2026Heqiang Qi, Wei Huang, Mingyuan Bai +1Masked Diffusion Language Models Diffusion Language Models
LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation
May 26, 2026Gabriele Cesa, Thomas Hehn, Aleix Torres-Camps +4Parallel LLM Inference Efficiency
Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining
May 26, 2026Biao Ouyang, Tengxue Zhang, Zhihao Zhuang +3Causal Foundation Models Temporal Dependence
Triplet-Block Diffusion RWKV
May 25, 2026Ke Lin, Yiyang Luo, Zhaolong Su +2Causal Attention Multimodal Diffusion Transformers
Function-Vector Heads Are Two Populations: Writers and Cancellers in In-Context Learning
May 25, 2026Han-yu WangAblation Causal Attention
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
May 22, 2026Chong Cheng, Peilin Tao, Nanjie Yao +93D Reconstruction Non-Rigid Shape Matching
CASE-NET: Deep Spatio-Temporal Representation Learning via Causal Attention and Channel Recalibration for Multivariate Time Series Classification
May 21, 2026Fan Zhang, Yating Cui, Hua WangTime-Series Classification Spatiotemporal Representations
Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting
May 18, 2026Antonio Colombo, Giovanni BianchiScene Text Recognition Rectification
WOW-Seg: A Word-free Open World Segmentation Model
May 16, 2026Danyang Li, Tianhao Wu, Bin Li +5Vision Foundation Models Causal Attention
DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer
May 15, 2026Nisha Huang, Yizhou Lin, Jie Guo +3Discrete Diffusion Model Causal Attention
Dynamic Chunking for Diffusion Language Models
May 15, 2026Yichen Zhu, Xiaoming Shi, Peng Zhao +3Diffusion Language Models Chunk
A Causal Language Modeling Detour Improves Encoder Continued Pretraining
May 12, 2026Rian Touchent, Eric de la ClergerieCausal Attention Model Pretraining

Sep 17, 2026 · cs.AIJ/K move · Enter open · S save

MaSCoD: A Multi-Agent Framework for Structural-Context-Guided Candidate Causal Graph Generation

Yudai Nakada, Yuichiro Nishiura, Jin Michael Splichal

Large language models (LLMs) have been applied to causal discovery, but candidate-graph generation rarely treats premature omission of potentially relevant causal relations as an explicit design objective. We propose MaSCoD, a multi-agent framework that organizes candidate third variables and local structural patterns before direct-edge judgment. We evaluate MaSCoD on Auto-MPG, DWD, and Sachs using GPT-5.4 as the primary backbone and GPT-4o for replication. MaSCoD exhibits a dataset- and backbone-dependent retention-selectivity profile rather than uniform superiority. Across all six dataset-backbone settings, Full, which supplies structural hypotheses before direct-edge judgment, achieved higher mean Recall and F1 than No Phase 1, which instead constructs them within the judgment procedure, while also increasing false-positive rates. Additional reference-edge retention over all evaluated baselines was observed on DWD with GPT-5.4 and on Sachs with GPT-4o, rather than uniformly across settings. Partial ablations showed that supplying both information components did not always outperform supplying only one. For GPT-5.4, stage-wise analysis showed that the Full-No Phase 1 retention gap was already present after direct-edge judgment, while reconciliation introduced additional reference-edge loss for Full on Sachs. These findings support structural pre-organization as an explicit design and evaluation target for omission control and motivate evaluating context construction jointly with its utilization in judgment.

Causal Graph Reasoning Graphs Causal Attention

Open paper Ask about it PDF