Paper Detail

Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation

Tirth Bhatt, Naren Kumar S, Mayank Singh

huggingface Score 10.4

Published 2026-08-06 · First seen 2026-08-08

General AI

Abstract

Multilingual text embedding models are commonly adapted using a single training objective across diverse tasks, despite different tasks requiring fundamentally different optimization strategies. We introduce Task-Conditional Flow Matching (TCFM), a multilingual embedding adaptation framework that selectively applies Flow Matching to translation tasks while optimizing retrieval, classification, and pair-classification tasks with objectives better aligned to their learning dynamics. TCFM further combines teacher-guided representation preservation with a three-stage curriculum to enable stable adaptation. Evaluated on the Indic Massive Text Embedding Benchmark, TCFM establishes a new state-of-the-art, consistently improving embedding quality across a diverse set of multilingual tasks and generalizing across embedding model families. We will publicly release the codebase and datasets upon acceptance of the paper.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{bhatt2026task,
  title = {Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation},
  author = {Tirth Bhatt and Naren Kumar S and Mayank Singh},
  year = {2026},
  abstract = {Multilingual text embedding models are commonly adapted using a single training objective across diverse tasks, despite different tasks requiring fundamentally different optimization strategies. We introduce Task-Conditional Flow Matching (TCFM), a multilingual embedding adaptation framework that selectively applies Flow Matching to translation tasks while optimizing retrieval, classification, and pair-classification tasks with objectives better aligned to their learning dynamics. TCFM further c},
  url = {https://huggingface.co/papers/2608.05785},
  keywords = {huggingface daily},
  eprint = {2608.05785},
  archiveprefix = {arXiv},
}

Metadata

{}