activity
20242026
collaborators

6 papers

cs.LG2026

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Yan Wang, Qifan Zhang, Jiachen Yu +12

Conventional LLMs keep the full KV cache loaded during decoding, causing a severe GPU memory bottleneck for ultra-long context serving. In this report, we propose \textbf{Lookahead…

cs.AI2026

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration

Qifan Zhang, Dongyang Ma, Tianqing Fang +5

Most agents today ``self-evolve'' by following rewards and rules defined by humans. However, this process remains fundamentally dependent on external supervision; without human gui…

cs.CL2026

NPG-Muse: Scaling Long Chain-of-Thought Reasoning with NP-Hard Graph Problems

Yuyao Wang, Bowen Liu, Jianheng Tang +6

Reasoning Large Language Models (RLLMs) have recently achieved remarkable progress on complex reasoning tasks, largely enabled by their long chain-of-thought (Long CoT) capabilitie…

cs.AI2026

Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems

Qifan Zhang, Jianhao Ruan, Aochuan Chen +4

Large Reasoning Models (LRMs) have advanced rapidly; however, existing benchmarks in mathematics, code, and common-sense reasoning remain limited. They lack long-context evaluation…

cs.AI2025

GraphArena: Evaluating and Exploring Large Language Models on Graph Computation

Jianheng Tang, Qifan Zhang, Yuhan Li +2

The ``arms race'' of Large Language Models (LLMs) demands new benchmarks to examine their progresses. In this paper, we introduce GraphArena, a benchmarking tool designed to evalua…

cs.CL2024

GCoder: Improving Large Language Model for Generalized Graph Problem Solving

Qifan Zhang, Xiaobin Hong, Jianheng Tang +5

Large Language Models (LLMs) have demonstrated strong reasoning abilities, making them suitable for complex tasks such as graph computation. Traditional reasoning steps paradigm fo…