AMO combines sim-to-real RL and trajectory optimization to enable high-DoF humanoid whole-body control with expanded workspace and O.O.D. adaptation.

Jialong Li, Xuxin Cheng, Tianshu Huang et al.

VIDEOMIMIC converts monocular videos into environment-conditioned humanoid control policies, enabling robots to perform complex behaviors like stair climbing and sitting in diverse settings.

Arthur Allshire, Hongsuk Choi, Junyi Zhang et al.

LlamaFirewall integrates PromptGuard 2, Agent Alignment Checks, and CodeShield to effectively defend against prompt injection, goal misalignment, and insecure code generation, enhancing AI agent security.

Sahana Chennabasappa, Cyrus Nikolaidis, Daniel Song et al.

A survey unifies CoT, RAG, and verifiers for complex LLM problem solving, but reports no new benchmark metrics.

Da Zheng, Lun Du, Junwei Su et al.

Proposes Absolute Zero, a zero-data reinforcement self-play framework with code-based reasoning, achieving SOTA in mathematical and coding tasks.

Andrew Zhao, Yiran Wu, Yang Yue et al.

MORE enhances zero-shot mobile manipulation planning via scene graphs and task-relevant subgraph filtering, outperforming baselines on BEHAVIOR-1K.

Mohammad Mohammadi, Daniel Honerkamp, Martin Büchner et al.

Guiding LLM behavior using reward signals, employing techniques like RLHF and RLAIF for dynamic feedback learning.

Xiaobao Wu

Unified multimodal model combining diffusion and autoregressive mechanisms, enhancing understanding and generation capabilities.

Shanshan Zhao, Xinjie Zhang, Jintao Guo et al.

El Agente Q, an LLM-based multi-agent system, autonomously executes quantum chemistry workflows with over 87% success rate.

Yunheng Zou, Austin H. Cheng, Abdulrahman Aldossary et al.

RM-R1 formulates reward modeling as a reasoning task using chain-of-thought and Rubrics, outperforming larger models by up to 4.9%.

Xiusi Chen, Gaotang Li, Ziqi Wang et al.

This study analyzes length bias in LLM-based MT evaluation, proposing FSP and fine-tuning to improve consistency across input granularities.

Tobias Domhan, Dawei Zhu

VLoRP introduces multi-grained low-rank gradient projection, enhancing memory efficiency and stability in large language model fine-tuning.

Yezhen Wang, Zhouhao Yang, Brian K Chen et al.

DetoxAI is a post-hoc debiasing toolkit for deep vision models, supporting state-of-the-art algorithms and fairness metrics, enhancing model fairness without retraining.

Ignacy Stępka, Lukasz Sztukiewicz, Michał Wiliński et al.

Proposes Modular GP-GOMEA with multi-tree evolution and subexpression reuse, boosting symbolic regression accuracy and interpretability.

Joe Harrison, Peter A. N. Bosman, Tanja Alderliesten

SynPAT generates synthetic physical theories with axioms, consequences, and noisy data, enabling robust benchmarking of symbolic regression systems.

Jonathan Lenchner, Karan Srivastava, Joao Goncalves et al.

SpatialLLM integrates 3D-aware data and multi-stage training, achieving 8.7% better than GPT-4o in 3D spatial reasoning tasks.

Wufei Ma, Luoxin Ye, Celso M de Melo et al.

Proposes RoVI for hand-drawn visual instructions, integrated with VIEW pipeline, achieving 87.5% success in complex robotic tasks.

Yanbang Li, Ziyang Gong, Haoyang Li et al.

DeepCritic introduces a two-stage framework leveraging Qwen2.5-72B-Instruct to enhance mathematical critique, outperforming GPT-4o and DeepSeek with significant accuracy gains.

Wenkai Yang, Jingwen Chen, Yankai Lin et al.

This study compares large language models' generalization in in-context learning vs. fine-tuning, proposing reasoning trace augmentation to improve performance.

Andrew K. Lampinen, Arslan Chaudhry, Stephanie C. Y. Chan et al.

Proposes COIL, modeling multi-task interactive learning as a UFL problem, reducing human effort by 23% in experiments.

Shivam Vats, Michelle Zhao, Patrick Callaghan et al.