Pith. sign in

REVIEW 5 cited by

ClusT3: Information Invariant Test-Time Training

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.12345 v1 pith:PLNZPP4N submitted 2023-10-18 cs.CV cs.AIcs.LG

Gustavo A. Vargas Hakim , David Osowiechi , Mehrdad Noori , Milad Cheraghalikhani , Ismail Ben Ayed , Christian Desrosiers This is my paper
classification cs.CVcs.AIcs.LG
keywords test-timetasktraininginformationperformanceadaptationattemptauxiliary
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep Learning models have shown remarkable performance in a broad range of vision tasks. However, they are often vulnerable against domain shifts at test-time. Test-time training (TTT) methods have been developed in an attempt to mitigate these vulnerabilities, where a secondary task is solved at training time simultaneously with the main task, to be later used as an self-supervised proxy task at test-time. In this work, we propose a novel unsupervised TTT technique based on the maximization of Mutual Information between multi-scale feature maps and a discrete latent representation, which can be integrated to the standard training as an auxiliary clustering task. Experimental results demonstrate competitive classification performance on different popular test-time adaptation benchmarks.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. NNGPT: Rethinking AutoML with Large Language Models

    cs.AI 2025-11 conditional novelty 5.0 of 10

    NNGPT is an LLM-driven AutoML system that generates executable PyTorch pipelines from a prompt and continuously fine-tunes itself on the results.

  2. Scientific-Intention Driven Embodied Intelligent Solar Telescope: Conceptual Design

    astro-ph.IM 2026-07 reject novelty 4.0 of 10

    A three-layer AI-agent design for intention-driven autonomous solar telescopes is proposed; only the precision temperature-control prototype was tested.

  3. Paged Attention Meets FlexAttention: Unlocking Long-Context Efficiency in Deployed Inference

    cs.LG 2025-06 conditional novelty 4.0 of 10

    The paper integrates PagedAttention with PyTorch FlexAttention inside IBM FMS and reports that this lowers long-context KV-cache memory overhead and keeps decode latency roughly linear when the KV cache is enabled.

  4. Multimodal Framework for Explainable Autonomous Driving: Integrating Video, Sensor, and Textual Data for Enhanced Decision-Making and Transparency

    cs.MM 2025-07 reject novelty 3.0 of 10

    A three-branch model (VideoMAE, a two-layer sensor MLP, BERT, fused into a BART-based explainer) reports 92.5% action accuracy and a 0.75 BLEU-4 on nuScenes, with simulated attention maps and no released code.

  5. Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges

    cs.AI 2025-07 reject novelty 1.0 of 10

    A broad survey of LLM alignment that catalogs objectives, benchmarks, SFT/RLHF/DPO methods, and safety challenges, without contributing new experimental or theoretical results.

Pith tools