◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Vasu Shyam

4 papers hereh-index 320 citations5 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author1
  • middle author3

Across the 4 of 4 papers where every author was matched, so the position is known.

fields
  • cs.CL2
  • cs.LG2

identity via Semantic Scholar / OpenAlex

collaborators

4 papers

cs.LG2026

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior

Daniel Wurgaft, Can Rager, Matthew Kowal +13

Neural representations carry rich geometric structure; but does that structure causally shape behavior? To address this question, we intervene along paths through activation space…

cs.LG2026

Do Sparse Autoencoders Capture Concept Manifolds?

Usha Bhalla, Thomas Fel, Can Rager +9

Sparse autoencoders (SAEs) are widely used to extract interpretable features from neural network representations, often under the implicit assumption that concepts correspond to in…

cs.CL2026

Folding Tensor and Sequence Parallelism for Memory-Efficient Transformer Training & Inference

Vasu Shyam, Anna Golubeva, Quentin Anthony

We present tensor and sequence parallelism (TSP), a parallel execution strategy that folds tensor parallelism and sequence parallelism onto a single device axis. In conventional mu…

cs.CL2025

Training Foundation Models on a Full-Stack AMD Platform: Compute, Networking, and System Design

Quentin Anthony, Yury Tokpanov, Skyler Szot +18

We report on the first large-scale mixture-of-experts (MoE) pretraining study on pure AMD hardware, utilizing both MI300X GPUs and Pollara networking. We distill practical guidance…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.