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 5

Submitted by

yangwang825

Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth

·
7 authors

Submitted by

xiaochonglinghu

From Editor to Dense Geometry Estimator

·
9 authors

Submitted by

XingtaiHF

Towards a Unified View of Large Language Model Post-Training

·
12 authors

Submitted by

haiyuanwan

DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks

·
13 authors

4

Submitted by

taesiri

Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

·
21 authors

Submitted by

Yiyuan

Transition Models: Rethinking the Generative Learning Objective

·
7 authors

Submitted by

Uri-ka

NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings

·
4 authors

Submitted by

TianshuiChen

Video-MTR: Reinforced Multi-Turn Reasoning for Long Video Understanding

·
4 authors

2

Submitted by

hxyscott

Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers

·
46 authors

2

Submitted by

thewhole

Few-step Flow for 3D Generation via Marginal-Data Transport Distillation

·
8 authors

2

Submitted by

HyunsooCha

Durian: Dual Reference-guided Portrait Animation with Attribute Transfer

·
3 authors

Submitted by

OscarXZQ

Delta Activations: A Representation for Finetuned Large Language Models

·
4 authors

Submitted by

1nnoh

Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings

·
6 authors

Submitted by

ZemingWei

False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize

·
4 authors

3