Revisiting Transformer Layer Parameterization Through Causal Energy Minimization
Jin Xu, Camille Couturier, Victor Ruhle, Saravan Rajmohan, James Hensman
May 2026
arXiv | May 2026
James Hensman
Sr Principal Researcher
论文与出版物
-
-
-
Scalable Model-Based Clustering with Sequential Monte Carlo
C. Trojan, Pavel Myshkov, P. Fearnhead, James Hensman, Tom Minka, Chris Nemeth
AISTATS 2026 | April 2026
-
-
-
TurboAttention: Efficient Attention Approximation For High Throughputs LLMs
Hao Kang, Srikant Bharadwaj, James Hensman, Tushar Krishna, Victor Ruehle, Saravan Rajmohan
ArXiv | December 2024
-
KBLaM: Knowledge Base augmented Language Model
Xi Wang, Liana Mikaelyan, Taketomo Isazawa, James Hensman
October 2024
ArXiv | October 2024
-
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Martin Jaggi, Dan Alistarh, Torsten Hoefler, James Hensman, Pashmina Cameron
Neural Information Processing Systems | March 2024
Preprint
-
-
-
Revisiting Transformer Layer Parameterization Through Causal Energy Minimization
Jin Xu, Camille Couturier, Victor Ruhle, Saravan Rajmohan, James Hensman
May 2026
arXiv | May 2026
-
Scalable Model-Based Clustering with Sequential Monte Carlo
C. Trojan, Pavel Myshkov, P. Fearnhead, James Hensman, Tom Minka, Chris Nemeth
AISTATS 2026 | April 2026
-
TurboAttention: Efficient Attention Approximation For High Throughputs LLMs
Hao Kang, Srikant Bharadwaj, James Hensman, Tushar Krishna, Victor Ruehle, Saravan Rajmohan
ArXiv | December 2024
-
KBLaM: Knowledge Base augmented Language Model
Xi Wang, Liana Mikaelyan, Taketomo Isazawa, James Hensman
October 2024
ArXiv | October 2024
-
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Martin Jaggi, Dan Alistarh, Torsten Hoefler, James Hensman, Pashmina Cameron
Neural Information Processing Systems | March 2024
Preprint
-
-
-
Revisiting Transformer Layer Parameterization Through Causal Energy Minimization
Jin Xu, Camille Couturier, Victor Ruhle, Saravan Rajmohan, James Hensman
May 2026
arXiv | May 2026
-
KBLaM: Knowledge Base augmented Language Model
Xi Wang, Liana Mikaelyan, Taketomo Isazawa, James Hensman
October 2024
ArXiv | October 2024
-
-
-
Scalable Model-Based Clustering with Sequential Monte Carlo
C. Trojan, Pavel Myshkov, P. Fearnhead, James Hensman, Tom Minka, Chris Nemeth
AISTATS 2026 | April 2026
-
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Martin Jaggi, Dan Alistarh, Torsten Hoefler, James Hensman, Pashmina Cameron
Neural Information Processing Systems | March 2024
Preprint
-
-
-
TurboAttention: Efficient Attention Approximation For High Throughputs LLMs
Hao Kang, Srikant Bharadwaj, James Hensman, Tushar Krishna, Victor Ruehle, Saravan Rajmohan
ArXiv | December 2024
-