Papers4

All Beginner Intermediate Advanced

All Sources arXiv

#context engineering

Large Multimodal Models as General In-Context Classifiers

Intermediate

Marco Garosi, Matteo Farina et al.Feb 26arXiv

People often pick CLIP-like models for image labeling, but this paper shows that large multimodal models (LMMs) can be just as good—or even better—when you give them a few examples in the prompt (in-context learning).

#in-context learning#multimodal models#open-world classification

ManCAR: Manifold-Constrained Latent Reasoning with Adaptive Test-Time Computation for Sequential Recommendation

Intermediate

Kun Yang, Yuxuan Zhu et al.Feb 23arXiv

ManCAR helps recommendation systems think step by step but keeps their thoughts on realistic paths using a map of how items connect.

#sequential recommendation#latent reasoning#interaction graph

LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth

Intermediate

Weihao Zeng, Yuzhen Huang et al.Feb 8arXiv

LOCA-bench is a test that challenges AI agents to work correctly as their to-do list and background information grow very, very long.

#LOCA-bench#long-context agents#context rot

Lost in the Noise: How Reasoning Models Fail with Contextual Distractors

Intermediate

Seongyun Lee, Yongrae Jo et al.Jan 12arXiv

The paper shows that when we give AI lots of extra text, even harmless extra text, it can get badly confused—sometimes losing up to 80% of its accuracy.

#NoisyBench#Rationale-Aware Reward#RARE