Yanlin Fu

I am working on BCI🧠 algos. TeX (and typography), Cognitive Science, Mathematical Logic, Market Microstructure and Linguistics. #PandemicIsNotOver.

[Yanlin Fu @ylfu02]

I am interested in these topics:
1. Cross Regime/Session timeseries prediction. Like cross-day/subject neural decoding and cross regime market cross section predictions.
2. Stochastic Process Modeling in Human Decision and derivative pricing .
3. Interpretable ML/DL/LLM theory.

[Yanlin Fu @ylfu02]

？我只见过只会用ai vibe啥都不会在简历上写react，因为简历也是AI写的，技术一问三不知

[Paul Linton @LintonVision]

🎥 Videos now available for:

COMPUTATIONAL CONSCIOUSNESS SCIENCE

A CCN satellite meeting, hosted and sponsored by the NYU Center for Mind, Brain, and Consciousness.

Website: https://t.co/pAFvbopg30

YouTube: https://t.co/BOuD9rnwbI

@CogCompNeuro @nyuconscious

[Alessandro Crimi 🧠🧬🔬🩺( @alecrimi.bsky.social ) @Dr_Alex_Crimi]

Since we are into visualization craze, here is one about🧠#stroke and lateralization. If you want, check the whole paper about gradients: "Reshaped functional connectivity gradients in acute ischemic stroke" https://t.co/1YMWfZQk6Q

[Yanlin Fu @ylfu02]

怎么还没有AI大手子定点爆破PRL，我真的等不及看某些人跳脚了。
PRC炸了PRL壬就开始搞鄙视链，我评价是PRL也该死了

[Yanlin Fu @ylfu02]

drift diffusion!
难绷真的能行为学拟合大部分人的梭哈偏好

[Yanlin Fu @ylfu02]

@xnggung89891482 wsl上用codex tui吧

[@BioAI_Neuro @BioAI_NeuralNet]

Real-time reinforcement for human-machine interface control
https://t.co/R0BsOOP45r

Summary

1. Real-time reinforcement improves motor performance: Personalized, closed-loop reinforcement feedback enhances force control during human–machine interface tasks.

2. Rapid learning: Fewer than 20 reinforcement trials produce immediate improvements in motor control.

3. Long-term retention: Improvements can persist after training, although retention gains were not observed after short training in chronic stroke patients.

4. Greater benefits with limited sensory feedback: Reinforcement is most effective when visual or somatosensory feedback is reduced.

5. Benefits for stroke patients: Real-time reinforcement improves online force control in chronic stroke patients under conditions of limited visual feedback.

6. Compensates for reduced feedback: Reinforcement helps maintain motor control when sensory information is sparse.

7. Promotes successful action selection: Reinforcement encourages individuals to repeat and exploit motor actions that produce successful outcomes.

8. Translational potential: This strategy could improve rehabilitation and control of human–machine interfaces, particularly for people with motor disabilities.

[Yanlin Fu @ylfu02]

我从kimi1.5开始对这家模型公司印象就很差（包括glm家从z1/glm4），倒是从deepseek-coder开始用感觉一直在进步。

[@BioAI_Neuro @BioAI_NeuralNet]

Cognitive computational neuroscience
https://t.co/36JzFigmF8

1/ Move beyond brain mapping.
Mapping which brain regions activate during a task is not enough to explain cognition. We need computational models that reproduce behavior and explain how neural activity generates perception, learning, decision-making, and action. The goal is to understand the mechanism, not just the location.

2/ Build models that perform cognitive tasks.
Allen Newell argued that understanding cognition requires constructing systems that actually perform the functions we want to explain. A theory of decision-making, for example, should predict choices under different conditions—not merely describe them verbally. Simulations help test whether proposed mechanisms work together to produce intelligent behavior.

3/ Integrate three disciplines.
Cognitive science explains the computations underlying thought; computational neuroscience investigates how neural circuits implement those computations; AI develops algorithms that perform complex tasks. Each provides different constraints. Combining them could produce models that are simultaneously behaviorally effective, computationally explicit, and biologically grounded.

4/ Neural networks are a bridge between brains and AI.
Deep neural networks learn hierarchical representations that can resemble those observed in biological sensory systems. Research has shown that networks trained for object recognition can predict aspects of visual cortical representations. However, predictive similarity does not prove that the brain uses the same algorithms. Models must also be tested against neural and behavioral evidence.

5/ Biological neurons offer more than artificial units.
Most conventional artificial neural networks use simplified units that combine inputs and apply nonlinear transformations. Biological neurons exhibit action potentials, dendritic computations, recurrent signaling, oscillations, and complex temporal dynamics. Incorporating these features into task-performing models may reveal computational principles that simpler AI architectures overlook.

6/ Neural decoding is not a complete explanation.
Decoding asks what information can be extracted from neural activity. Encoding models predict neural responses; representational similarity analysis compares patterns of activity; connectivity models examine interactions. These methods constrain theories, but they do not necessarily explain how the brain transforms information to solve a task. Mechanistic models must connect representations to computation and behavior.

7/ Bayesian inference offers a theory of perception and reasoning.
The brain must interpret noisy sensory information using prior knowledge about the world. Bayesian models formalize this process by combining prior beliefs with incoming evidence. Generative models go further by representing how hidden causes produce observations. They offer a framework for studying uncertainty, causal reasoning, concept formation, and the ability to learn from limited experience.
8/ Learning and control require multiple strategies.
Reinforcement learning provides a framework for understanding how actions and feedback shape future behavior. Model-free approaches learn values or policies from experience; model-based approaches use an internal model to evaluate possible outcomes; episodic approaches reuse specific past experiences. Understanding how biological brains combine these strategies could inform more adaptive AI systems.

9/ Combine bottom-up and top-down approaches.
Bottom-up neuroscience begins with neurons, circuits, and measured activity. Top-down approaches begin with a cognitive function and ask what computations are required to perform it. Neither is sufficient alone. Strong theories should explain how biological mechanisms support meaningful behavior—and use behavioral requirements to identify which neural mechanisms matter.

10/ The future is an integrated NeuroAI.
A major challenge is to connect three levels: computational goals, representations and algorithms, and neurobiological implementation. This requires collaboration across neuroscience, cognitive science, mathematics, and AI, along with shared datasets, models, tasks, and evaluation methods. The ultimate ambition is to build systems that perform intelligent tasks while explaining how brains learn, represent knowledge, and adapt.

The big idea:
The next leap in AI and neuroscience may come from treating the brain not simply as a source of data, but as a system whose computational principles can be tested through models that connect neural mechanisms to intelligent behavior.

[马里奥 @itsMarioJJ]

@chumacn 说白了就是没造血能力，全靠融来的钱在那死扛

[Yanlin Fu @ylfu02]

In July GPT5.6 Sol setup a parameter-matched ablation with strange 256to1068to4 for me but everything on lr scheduling follows karpathy’s advice. But now astra prefer no scheduling with fixed lr makes me annoying.

[Ziming Liu @ZimingLiu11]

Humans can still surpass LLMs in training intuition (in some cases).

Indeed, Kaiming He used his intuition to create ResNet, without producing 1M-token CoT like today's LLMs do.

Introducing Architecture IQ -- Measuring training intuition. Even top LLMs are far from perfect.

[Haldun Balim @haldunbalim1]

What if embodied agents could learn to plan instead of just learning how to act? 🧠🤖

Introducing Generative Trajectory Planning (GTP)! 🚀

Instead of learning policies through RL, GTP imagines possible futures, plans ahead, and learns to plan better through experience.

[Yanlin Fu @ylfu02]

绷…

[lifcc @mylifcc]

@CalStonebreaker 我已经丧失说第二句话的权利了。。。

[Yanlin Fu @ylfu02]

救命，怎么神人这么多

[Yanlin Fu @ylfu02]

怎么还公开处刑了applications to neuroscience track的文章（

[Gautam Kamath @thegautamkamath]

How do you tell if authors fabricated their research results? Sometimes: they just tell you. Read, e.g., this caption carefully.

Another banger of a post by my friend Nihar B. Shah on his blog, where he found at least 20+ such #ICLR2027 submissions:
https://t.co/TBKmnMjTiy

[Yanlin Fu @ylfu02]

Great Job! Cannot wait trying to align EEG decoded human selected visual attention with this!

[Yijun Shen (沈逸骏) @bui_thanh64689]

Our latest paper, “World Models with Configurable Perception”, explores configurable states as information bottlenecks for robust planning in noisy worlds.
⬇️
Paper: https://t.co/YqvjITUeSp
Web: https://t.co/piXqdM2nhK
Code: https://t.co/6VnlnRnNJe
Data: https://t.co/7J8f74Qsbt

[Yanlin Fu @ylfu02]

@lianda_edu 看实习生简历中，大概就是一篇paper工作全写自己身上但是连个一千零一作都没有，最难绷的是ta在的实验室老板我就认识...

[Yanlin Fu @ylfu02]

在这个简历大包装时代只能说要诈骗也最好去大圈子诈骗，小圈子真的是开盒各种不超过半小时，结果到底是不是瞎几把吹一下子就知道了。