Zixi "Oz" Li
OzTianlu
AI & ML interests
My research focuses on deep reasoning with small language models, Transformer architecture innovation, and knowledge distillation for efficient alignment and transfer.
Recent Activity
reacted
to
their
post
with π
about 4 hours ago
π Geilim-1B-Instruct β Implicit Deep Reasoning, Zero Verbosity
https://huggingface.co/NoesisLab/Geilim-1B-Instruct
https://huggingface.co/collections/NoesisLab/geilim-large-language-models
No <think> tags. No long CoT.
Reasoning happens inside the hidden states, not in the output.
Whatβs different
π§ Implicit reasoning: deep causal reasoning without exposing chains
πΈοΈ ASPP (Adjacency-Structured Parallel Propagation): parent-only causal graph, O(n) message passing
π Ο-flow: internal probability-space refinement instead of token-level deliberation
βοΈ Hybrid gating: learns when to use structure vs attention
Why it matters
Lower latency & token cost
Cleaner, production-ready outputs
CoT-level reasoning depth without verbosity tax
Built on Llama-3.2-1B-Instruct, trained for math, logic, and commonsense.
Designed for small-model reasoning at the edge.
#ImplicitReasoning #SmallLLM #EfficientAI #ReasoningModels #ASPP #PiFlow
posted
an
update
about 4 hours ago
π Geilim-1B-Instruct β Implicit Deep Reasoning, Zero Verbosity
https://huggingface.co/NoesisLab/Geilim-1B-Instruct
https://huggingface.co/collections/NoesisLab/geilim-large-language-models
No <think> tags. No long CoT.
Reasoning happens inside the hidden states, not in the output.
Whatβs different
π§ Implicit reasoning: deep causal reasoning without exposing chains
πΈοΈ ASPP (Adjacency-Structured Parallel Propagation): parent-only causal graph, O(n) message passing
π Ο-flow: internal probability-space refinement instead of token-level deliberation
βοΈ Hybrid gating: learns when to use structure vs attention
Why it matters
Lower latency & token cost
Cleaner, production-ready outputs
CoT-level reasoning depth without verbosity tax
Built on Llama-3.2-1B-Instruct, trained for math, logic, and commonsense.
Designed for small-model reasoning at the edge.
#ImplicitReasoning #SmallLLM #EfficientAI #ReasoningModels #ASPP #PiFlow
liked
a model
about 9 hours ago
NoesisLab/Geilim-1B-Instruct
Organizations
