·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism3h◆Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking3h◆Critique of Agent Model3h◆LemonHarness Technical Report3h◆Random coloured digraphs defined by a Markov logic network3h◆Weight-Space Geometry of Offline Reasoning Training3h◆The Measurable Majority3h◆Fast and Slow Variational Continual Learning3h◆Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation3h◆Task Decomposition for Efficient Annotation3h◆Grounded Chess Reasoning in Language Models via Master Distillation3h◆Efficient Test-time Inference for Generative Planning Models with OCL Search3h◆CRAFT: A Tendon-Driven Hand with Hybrid Hard-Soft Compliance3h◆L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Models3h◆EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering3h◆Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal3h◆FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filters3h◆Lightweight Test-Time Adaptation for EMG-Based Gesture Recognition3h◆Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks3h◆A Theory of Saddle Escape in Deep Nonlinear Networks3h◆Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism3h◆Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking3h◆Critique of Agent Model3h◆LemonHarness Technical Report3h◆Random coloured digraphs defined by a Markov logic network3h◆Weight-Space Geometry of Offline Reasoning Training3h◆The Measurable Majority3h◆Fast and Slow Variational Continual Learning3h◆Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation3h◆Task Decomposition for Efficient Annotation3h◆Grounded Chess Reasoning in Language Models via Master Distillation3h◆Efficient Test-time Inference for Generative Planning Models with OCL Search3h◆CRAFT: A Tendon-Driven Hand with Hybrid Hard-Soft Compliance3h◆L3Cube-MahaPOS: A Marathi Part-of-Speech Tagging Dataset and BERT Models3h◆EvidenceLens: A Claim-Evidence Matrix for Auditing Financial Question Answering3h◆Light-weight Pronunciation Assessment via Discrete Speech Token Surprisal3h◆FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filters3h◆Lightweight Test-Time Adaptation for EMG-Based Gesture Recognition3h◆Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks3h◆A Theory of Saddle Escape in Deep Nonlinear Networks3h◆
News/LiFT: Does Instruction Fine-Tuning Improve In-Context Learning for Longitudinal Modelling by Large Language Models?
arxiv
PublishedApril 21, 2026 at 4:00 AM

LiFT: Does Instruction Fine-Tuning Improve In-Context Learning for Longitudinal Modelling by Large Language Models?

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2604.16382v1 Announce Type: new Abstract: Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-context learning with large language models struggles on tasks where models must integrate historical con

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivSpeculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism3harxivBlock-wise Codeword Embedding for Reliable Multi-bit Text Watermarking3harxivCritique of Agent Model3harxivLemonHarness Technical Report3h
The Bubble Brief
WEEKLY

Read AI insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews