arXiv Machine Learning June 24, 2026 By Siqi Zeng, Yifei He, Meitong Liu, Weiqiu You, Yifan Hao, Yao-Hung Hubert Tsai, Makoto Yamada, Han Zhao

Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic

Read the original on arXiv Machine Learning →

arXiv:2502. 01015v5 Announce Type: replace Abstract: Task arithmetic, representing downstream tasks through linear operations on task vectors, has emerged as a simple yet powerful paradigm for transferring knowledge across diverse settings.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 6

Attention-based representations for multi-task computation

arXiv:2608. 04243v1 Announce Type: new Abstract: Multi-head attention layers produce vector representations that support multiple downstream tasks.

By Daniel Hsu, Mingyue Xu

rag

arXiv AI

Aug 12

TACTICL: Task-Aware Compression of Tabular ICL Models

arXiv:2608. 10837v1 Announce Type: cross Abstract: The strong performance of foundation models for tabular tasks comes at substantial inference costs.

By Mykhailo Koshil, Matthias Feurer, Katharina Eggensperger

llms benchmarks

arXiv Machine Learning

Jun 18

PACT: Preserving Anchored Cores in Task-vectors for Model Merging

arXiv:2606. 18627v1 Announce Type: new Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model.

By Ningyuan Shi, Zhipeng Zhou, Hao Wang, Chunyan Miao, Peilin Zhao

fine-tuning benchmarks

arXiv Machine Learning

6d ago

Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms

arXiv:2505. 23696v2 Announce Type: replace Abstract: Solving systems of polynomial equations, particularly those with finitely many solutions, is a crucial challenge across many scientific fields.

By Hiroshi Kera, Nico Pelleriti, Yuki Ishihara, Max Zimmer, Sebastian Pokutta

llms rag nlp

arXiv AI

Jun 30

HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression

arXiv:2606. 28831v1 Announce Type: cross Abstract: Long-context LLM inference faces a fundamental conflict: head-adaptive compression algorithms (e.

By Yuxuan Yang, Feiyang Ren, Bowen Zeng, Dalin Zhang, Jinpeng Chen, Gang Chen, Huan Li

llms efficiency benchmarks

arXiv Machine Learning

Aug 4

Gram-Space: Structure-Preserving Codebook Compression for Memory-Efficient Neuro-Symbolic AI

arXiv:2608. 01528v1 Announce Type: new Abstract: Vector symbolic architectures (VSA) are widely used for reasoning in neuro-symbolic (NeSy) AI, yet high-dimensional codebooks often create severe memory bottlenecks that limit scalability and deployment.

By Weilun Wang, Wantong Li

efficiency benchmarks

Related stories

Attention-based representations for multi-task computation

TACTICL: Task-Aware Compression of Tabular ICL Models

PACT: Preserving Anchored Cores in Task-vectors for Model Merging

Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms

HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression

Gram-Space: Structure-Preserving Codebook Compression for Memory-Efficient Neuro-Symbolic AI