new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Sep 18

Submitted by

hammh0a

Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale

·
3 authors

Submitted by

taesiri

SAIL-VL2 Technical Report

·
14 authors

Submitted by

Chenfei-Liao

PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era

·
15 authors

Submitted by

taesiri

GenExam: A Multidisciplinary Text-to-Image Exam

·
8 authors

Submitted by

chuzy

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning

·
10 authors

Submitted by

AdinaY

MedReseacher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework

·
15 authors

Submitted by

taesiri

THOR: Tool-Integrated Hierarchical Optimization via RL for Mathematical Reasoning

·
9 authors

Submitted by

taesiri

MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

·
128 authors

Submitted by

taesiri

Wan-Animate: Unified Character Animation and Replacement with Holistic Replication

·
26 authors

Submitted by

sheryc

Improving Context Fidelity via Native Retrieval-Augmented Reasoning

·
9 authors

Submitted by

samforeman

AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions

·
15 authors

1

Submitted by

ncrispino

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs

·
8 authors

1

Submitted by

Jim137

Quantum Variational Activation Functions Empower Kolmogorov-Arnold Networks

·
4 authors

Submitted by

Akhil-Theerthala

Synthesizing Behaviorally-Grounded Reasoning Chains: A Data-Generation Framework for Personal Finance LLMs

·
1 authors

1

Submitted by

kkwok

LLM-I: LLMs are Naturally Interleaved Multimodal Creators

·
4 authors

1

Submitted by

qiuqiu99

WildSmoke: Ready-to-Use Dynamic 3D Smoke Assets from a Single Video in the Wild

·
4 authors

1

Submitted by

vaidehi99

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration

·
3 authors

Submitted by

nielsr

Image Tokenizer Needs Post-Training

·
10 authors

Submitted by

adnanphp

Hybrid Quantum-Classical Model for Image Classification

·
1 authors