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

Aug 25

Submitted by

taesiri

AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMs

·
11 authors

Submitted by

MasterVito

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

·
7 authors

Submitted by

MingyuLiu

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks

·
10 authors

2

Submitted by

taesiri

AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

·
23 authors

Submitted by

liuziwei7

EgoTwin: Dreaming Body and View in First Person

·
8 authors

2

Submitted by

zhwang01

AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions

·
28 authors

4

Submitted by

Tomertech

CRISP: Persistent Concept Unlearning via Sparse Autoencoders

·
5 authors

2

Submitted by

hynnsk

Selective Contrastive Learning for Weakly Supervised Affordance Grounding

·
3 authors

Submitted by

chaoyi-wu

End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

·
10 authors

Submitted by

taesiri

Do What? Teaching Vision-Language-Action Models to Reject the Impossible

·
6 authors

Submitted by

fxmeng

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill \& Decode Inference

·
7 authors

2

Submitted by

GuangcongWang

Distilled-3DGS:Distilled 3D Gaussian Splatting

·
4 authors

Submitted by

Okrin

Sketch3DVE: Sketch-based 3D-Aware Scene Video Editing

·
5 authors

Submitted by

taesiri

InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Styles

·
11 authors

Submitted by

Qlisp

CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning

·
5 authors

3

Submitted by

Charlie019

Learnable SMPLify: A Neural Solution for Optimization-Free Human Pose Inverse Kinematics

·
5 authors

Submitted by

odinhg

RotaTouille: Rotation Equivariant Deep Learning for Contours

·
2 authors

Submitted by

AlienZhang1996

Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts

·
6 authors