Proposes Shallow-RHS, an asymmetric graph architecture for cold-start content recommendation, mapping intrinsic features into a collaborative filtering space for immediate deployment.

Anh Truong, John Trenkle, Yuanbo Chen et al.

Proposes Hub-Aware hybrid search combining pre-processing and likelihood-pheromone guidance to enhance cosmic web filament detection efficiency.

Simone Vilardi, Reynier Peletier, Felipe Contreras et al.

Proposes iCEM+TL framework integrating transfer learning to boost low-level robotic motion planning success rate by 23%, enabling zero-shot transfer for complex tasks.

Yuanzhi He, Victor Romero-Cano, José J. Patiño et al.

MolE-RAG integrates literature, molecular features, and structural similarity to enhance LLM-based molecular property prediction, boosting ROC-AUC by up to 28% and reducing RMSE by 67%.

Joey Chan, Wonbin Kweon, Ashley Shin et al.

Proposes DistIL, a distributional imitation learning algorithm with monotonic improvement guarantees, leveraging rich feedback for complex reasoning tasks.

Rishabh Agrawal, Jacob Fein-Ashley, Paria Rashidinejad

Humanoid-GPT employs a 2B-frame large-scale motion dataset and GPT-style causal Transformer to achieve zero-shot high-dynamic motion tracking, surpassing shallow MLP trackers.

Zekun Qi, Xuchuan Chen, Dairu Liu et al.

Skill-RM unifies heterogeneous evaluation criteria via agent skills, enabling dynamic resource orchestration, outperforming traditional judges with a 3-6% improvement on RewardBench2.

Tao Chen, Gangwei Jiang, Pengyu Cheng et al.

Introducing the 'Sleep' paradigm with Knowledge Seeding and Dreaming mechanisms enables LLMs to self-modify and consolidate memories for continual learning.

Ali Behrouz, Farnoosh Hashemi, Vahab Mirrokni

Proposes ROSA, a reward distribution-based framework for inducing diverse behaviors without performance loss, leveraging set functions and unbiased gradient estimators.

Anthony GX-Chen, Ankit Anand, Gheorghe Comanici et al.

Proposed PACT framework uses preference signals and task progress modeling to correct overestimated Q-values, boosting success rate by 24.5% and accelerating convergence 1.3× in real robot tasks.

Zeyi Liu, Guangyao Liu, Yinuo Qu et al.

SEAOTTER combines a low-complexity learned latent encoder with a learnable JPEG codec and one-time cloud transcode, achieving 200:1 compression with 7× faster encoding, 3.5× decoding, and 8% accuracy boost on ImageNet.

Dan Jacobellis, Neeraja J. Yadwadkar

This paper introduces an equilibrium propagation (EP)-based training method for deep predictive coding networks (PCNs), achieving 13.23% Top-5 error on ImageNet with a 10-layer VGG model, close to the 12.2% baseline of backpropagation.

Tugdual Kerjan, Rasmus Høier, Benjamin Scellier

Proposes SEIG, a staged framework leveraging pretrained vision-language models (VLMs) to reconstruct editable 3D scenes from a single image, achieving high fidelity in geometry, materials, and lighting.

Guangzhao He, Rundong Luo, Wei-Chiu Ma et al.

AdaCodec employs predictive visual coding, transmitting full reference frames only when prediction is costly, reducing visual tokens by 84.7% and boosting long-video understanding efficiency.

Haowen Hou, Zhen Huang, Zheming Liang et al.

This paper introduces VLM as a teacher for video reasoning via test-time online optimization, achieving a 16.7-point performance boost, surpassing traditional methods.

Junhao Cheng, Liang Hou, Tianxiong Zhong et al.

SubFit introduces non-contiguous submodule replacement in LLMs, achieving superior compression with 84.6% accuracy at 25% sparsity, using residual fitting without retraining.

Elia Cunegatti, Marcus Vukojevic, Erik Nielsen et al.

Proposed Script-Normalized WER (SN-WER), reducing script mismatch inflation by up to 12% across five Indic languages, enhancing multi-script ASR evaluation accuracy.

Priyaranjan Pattnayak

SimSD employs a plug-and-play masking strategy to enable token-level speculative decoding in diffusion LLMs, achieving up to 7.46× speedup while maintaining quality.

Junxia Cui, Haotian Ye, Runchu Tian et al.

SafeSteer employs localized on-policy distillation focusing on safety tokens, reducing reliance on large datasets and auxiliary reward models, achieving a superior safety-capability trade-off.

Hao Li, Jingkun An, Zijun Song et al.

Iteris employs an explore-plan-execute loop with multi-agent collaboration to generate numerical evidence and proof drafts, verified through expert review, advancing open problems in computational mathematics.

Leheng Chen, Zihao Liu, Wanyi He et al.