5 papers
Self-Improving is Often Sudden: Enlightenment-style Finetuning for Large-Scale Models
Jing-Xiao Liao, Tianwei Zhang, Yu-Hao Jiang +3
The pursuit of autonomously self-improving models has attracted growing interest in the era of large-scale foundation models. Drawing inspiration from the concept of "enlightenment…
Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models
Aiwei Liu, Cheng Shi, Chuhan Wu +44
Scaling Large Language Models (LLMs) has been driven mainly by enlarging the Transformer backbone, but for an already-strong model this requires another round of costly pretraining…
ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
Hao Wen, Yifan Su, Feifei Zhang +4
Recent advances in Large Language Models (LLMs) have been driven by test-time compute scaling - a strategy that improves reasoning by generating longer, sequential thought processe…
BudgetThinker: Empowering Budget-aware LLM Reasoning with Control Tokens
Hao Wen, Xinrui Wu, Yi Sun +7
Recent advancements in Large Language Models (LLMs) have leveraged increased test-time computation to enhance reasoning capabilities, a strategy that, while effective, incurs signi…
Tempo-R0: A Video-MLLM for Temporal Video Grounding through Efficient Temporal Sensing Reinforcement Learning
Feng Yue, Zhaoxing Zhang, Junming Jiao +4
Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of…