PhD student @ UCAS. Focusing on Long Context Modeling
Repositories
Xnhyacinth/Awesome-LLM-Long-Context-Modeling
๐ฐ Must-read papers and blogs on LLM based Long Context Modeling ๐ฅ
Xnhyacinth/Xnhyacinth.github.io
I'm here! ๐ Personal Home Page ๐๐
Xnhyacinth/OPERATE
Benchmarking Persistent Operational Agency in Source-Grounded Executable Systems
Xnhyacinth/NesyCD
[AAAI 2025] Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
Xnhyacinth/ScientistsLastExam
Xnhyacinth/cl
Xnhyacinth/SKIntern
[COLING 2025] SKIntern: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models
Xnhyacinth/Awesome-Latent-Reasoning
๐ฅ Must-read papers for LLM-based Latent Reasoning
Xnhyacinth/moon_eval
Xnhyacinth/HyCo2
Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention
Xnhyacinth/zotero-arxiv-daily
Recommend new arxiv papers of your interest daily according to your Zotero libarary.
Xnhyacinth/kvpress
LLM KV cache compression made easy
Xnhyacinth/AMD-Spark
Xnhyacinth/ResAdapt
ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning
Xnhyacinth/SpaRTA
[ACL 2026 Main] Spectral Disentanglement: Rank-Aware Task Adaptation for Rehearsal-free Continual Learning in LLMs
Xnhyacinth/wechat-public-account-push
some surprise
Xnhyacinth/threejs-games
Three.js games generated by multi-round AI benchmark: Arena Zero (FPS 5v5) + Rune Frontline (3D tower defense). Playable in browser.
Xnhyacinth/TAGI
[NeurIPS 2024] From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
Xnhyacinth/SparK
[AAAI 2026] SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
Xnhyacinth/IAG
[COLING 2025] Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering
Xnhyacinth/Cascotd
Xnhyacinth/Program
Xnhyacinth/LLMR
Xnhyacinth/LMTuner
Lingo: Make the LLM Better for Everyone
Xnhyacinth/rag_survey
Xnhyacinth/MyArxiv
Xnhyacinth/deep-learning-project-template
Pytorch Lightning code guideline for conferences