November 4, 2025 at 8:04 PM
fire rate vs controllability is kind of funny because low fire rates are controllable (you can regain your aim after each shot) and high fire rates are controllable (the recoil is more like a constant push) but there is an intermediate zone that just sprays wildly
October 25, 2025 at 5:33 PM
fire rate vs controllability is kind of funny because low fire rates are controllable (you can regain your aim after each shot) and high fire rates are controllable (the recoil is more like a constant push) but there is an intermediate zone that just sprays wildly
Here are some fun statistics from my weekend project. Look how steerable Qwen 3 0.6B is! With an R² of .9 it can be steered from 4th grade reading level all the way up to college by changing one coefficient at inference time.
Here's "What is AdS/CFT correspondence?" steered toward grades 5 and 17.
Here's "What is AdS/CFT correspondence?" steered toward grades 5 and 17.
October 20, 2025 at 8:59 PM
Here are some fun statistics from my weekend project. Look how steerable Qwen 3 0.6B is! With an R² of .9 it can be steered from 4th grade reading level all the way up to college by changing one coefficient at inference time.
Here's "What is AdS/CFT correspondence?" steered toward grades 5 and 17.
Here's "What is AdS/CFT correspondence?" steered toward grades 5 and 17.
In this behemoth effort led by @anhhtran.bsky.social, we reanalysed 11 experience-sampling datasets, and found limited evidence that context (intensity, controllability, and social features) meaningfully shaped everyday emotion regulation strategy use.
Context Matters, Doesn't It? The Role of Context in Everyday Emotion Regulation Strategy Use: https://osf.io/axzk6
October 13, 2025 at 3:45 AM
In this behemoth effort led by @anhhtran.bsky.social, we reanalysed 11 experience-sampling datasets, and found limited evidence that context (intensity, controllability, and social features) meaningfully shaped everyday emotion regulation strategy use.
3/6 We propose building models that explicitly capture social cognition (such as inferring others' beliefs, emotions, and intentions) along with contextual factors like fairness norms or controllability, while also incorporating domain-general processes like attention biases or prediction errors.
October 13, 2025 at 9:09 PM
3/6 We propose building models that explicitly capture social cognition (such as inferring others' beliefs, emotions, and intentions) along with contextual factors like fairness norms or controllability, while also incorporating domain-general processes like attention biases or prediction errors.
Had a great time presenting our work on the curse of dimensionality in network controllability @bernsteinneuro.bsky.social
Thanks samirsuweis.bsky.social and organizers for setting up this special event and for the smooth organization.
Low-dimensional controllability of brain networks t.ly/qosuT
Thanks samirsuweis.bsky.social and organizers for setting up this special event and for the smooth organization.
Low-dimensional controllability of brain networks t.ly/qosuT
Low-dimensional controllability of brain networks
Author summary Identifying control nodes in complex networks is essential for understanding and influencing biological systems. However, existing network control methods often fall short when the numb...
journals.plos.org
October 11, 2025 at 12:45 PM
Had a great time presenting our work on the curse of dimensionality in network controllability @bernsteinneuro.bsky.social
Thanks samirsuweis.bsky.social and organizers for setting up this special event and for the smooth organization.
Low-dimensional controllability of brain networks t.ly/qosuT
Thanks samirsuweis.bsky.social and organizers for setting up this special event and for the smooth organization.
Low-dimensional controllability of brain networks t.ly/qosuT
Reach out if you'd like to discuss anything related to model interpretability and controllability, robustness, multi-agent communication, biological LMs, etc.
Also happy to talk about PhD and Post-doc opportunities!
Also happy to talk about PhD and Post-doc opportunities!
October 7, 2025 at 1:41 PM
Reach out if you'd like to discuss anything related to model interpretability and controllability, robustness, multi-agent communication, biological LMs, etc.
Also happy to talk about PhD and Post-doc opportunities!
Also happy to talk about PhD and Post-doc opportunities!
(3) With the above two-stage models excelling in motion controllability and degree, we decouple the relevant parameters associated with each type of motion ability and inject them into the base I2V-DM. Since the I2V-DM [6/8 of https://arxiv.org/abs/2503.00948v1]
March 5, 2025 at 6:18 AM
(3) With the above two-stage models excelling in motion controllability and degree, we decouple the relevant parameters associated with each type of motion ability and inject them into the base I2V-DM. Since the I2V-DM [6/8 of https://arxiv.org/abs/2503.00948v1]
Xijun Wang, Dongshan Ye, Chenyuan Feng, Howard H. Yang, Xiang Chen, Tony Q. S. Quek
Trustworthy Image Semantic Communication with GenAI: Explainablity, Controllability, and Efficiency
https://arxiv.org/abs/2408.03806
Trustworthy Image Semantic Communication with GenAI: Explainablity, Controllability, and Efficiency
https://arxiv.org/abs/2408.03806
August 8, 2024 at 4:02 AM
Xijun Wang, Dongshan Ye, Chenyuan Feng, Howard H. Yang, Xiang Chen, Tony Q. S. Quek
Trustworthy Image Semantic Communication with GenAI: Explainablity, Controllability, and Efficiency
https://arxiv.org/abs/2408.03806
Trustworthy Image Semantic Communication with GenAI: Explainablity, Controllability, and Efficiency
https://arxiv.org/abs/2408.03806
💯
Should be on a short leash regardless of controllability when other animals are around.
Should be on a short leash regardless of controllability when other animals are around.
April 4, 2025 at 5:26 PM
💯
Should be on a short leash regardless of controllability when other animals are around.
Should be on a short leash regardless of controllability when other animals are around.
such a centrality index and can give a physically meaningful measure. Nevertheless, the existing work is limited to linear time-invariant systems and the controllability score cannot be applied to linear time-varying systems, which include [2/5 of https://arxiv.org/abs/2501.13345v1]
January 24, 2025 at 6:14 AM
such a centrality index and can give a physically meaningful measure. Nevertheless, the existing work is limited to linear time-invariant systems and the controllability score cannot be applied to linear time-varying systems, which include [2/5 of https://arxiv.org/abs/2501.13345v1]
Neuron Empirical Gradient: Connecting Neurons' Linear Controllability and Representational Capacity
Neuron activations in PLMs encode factual knowledge quantitatively, improving understanding of knowledge representation in language models.
Read more: https://arxiv.org/html/2412.18053v1
Neuron activations in PLMs encode factual knowledge quantitatively, improving understanding of knowledge representation in language models.
Read more: https://arxiv.org/html/2412.18053v1
January 6, 2025 at 3:42 PM
Neuron Empirical Gradient: Connecting Neurons' Linear Controllability and Representational Capacity
Neuron activations in PLMs encode factual knowledge quantitatively, improving understanding of knowledge representation in language models.
Read more: https://arxiv.org/html/2412.18053v1
Neuron activations in PLMs encode factual knowledge quantitatively, improving understanding of knowledge representation in language models.
Read more: https://arxiv.org/html/2412.18053v1
And if you mean for our replicas, the answer is controllability. The sheer volume of open fired pottery and the fact that the pots are often quite labour intensive, mean that we have to lower the risk of failure as far as possible. We supply major museums and institutions & need to meet deadlines.
March 7, 2025 at 6:20 PM
And if you mean for our replicas, the answer is controllability. The sheer volume of open fired pottery and the fact that the pots are often quite labour intensive, mean that we have to lower the risk of failure as far as possible. We supply major museums and institutions & need to meet deadlines.
[13/30] 216 Likes, 41 Comments, 4 Posts
2503.09573, cs․LG | cs․AI, 12 Mar 2025
🆕Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Marianne Arriola, Aaron Gokaslan, Justin T Chiu, Zhihan Yang, Zhixuan Qi, Jiaqi Han, Subham Sekhar Sahoo, Volodymyr Kuleshov
2503.09573, cs․LG | cs․AI, 12 Mar 2025
🆕Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Marianne Arriola, Aaron Gokaslan, Justin T Chiu, Zhihan Yang, Zhixuan Qi, Jiaqi Han, Subham Sekhar Sahoo, Volodymyr Kuleshov
March 15, 2025 at 12:05 AM
[13/30] 216 Likes, 41 Comments, 4 Posts
2503.09573, cs․LG | cs․AI, 12 Mar 2025
🆕Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Marianne Arriola, Aaron Gokaslan, Justin T Chiu, Zhihan Yang, Zhixuan Qi, Jiaqi Han, Subham Sekhar Sahoo, Volodymyr Kuleshov
2503.09573, cs․LG | cs․AI, 12 Mar 2025
🆕Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models
Marianne Arriola, Aaron Gokaslan, Justin T Chiu, Zhihan Yang, Zhixuan Qi, Jiaqi Han, Subham Sekhar Sahoo, Volodymyr Kuleshov
Using the well-established trauma film paradigm (TFP), we found that expectations about the intensity and controllability of intrusions influence their occurrence.👇🏻
link.springer.com/article/10.1...
#PsychSky #AcademicSky #PsychSciSky #Trauma
link.springer.com/article/10.1...
#PsychSky #AcademicSky #PsychSciSky #Trauma
November 18, 2024 at 12:38 PM
Using the well-established trauma film paradigm (TFP), we found that expectations about the intensity and controllability of intrusions influence their occurrence.👇🏻
link.springer.com/article/10.1...
#PsychSky #AcademicSky #PsychSciSky #Trauma
link.springer.com/article/10.1...
#PsychSky #AcademicSky #PsychSciSky #Trauma
models rely on U-Net, which underperforms compared to the MM-DiT; and (2) the neglect of textual information, which can enhance controllability. In this work, we introduce DynamiCtrl, a novel framework that not only explores different pose-guided [2/7 of https://arxiv.org/abs/2503.21246v1]
March 28, 2025 at 6:02 AM
models rely on U-Net, which underperforms compared to the MM-DiT; and (2) the neglect of textual information, which can enhance controllability. In this work, we introduce DynamiCtrl, a novel framework that not only explores different pose-guided [2/7 of https://arxiv.org/abs/2503.21246v1]
[2025-07-22] 📚 Updates in #CoGe
(1) <a href="https://researchtrend.ai/papers/2410.12601" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
(2) CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
🔍 More at researchtrend.ai/communities/CoGe
(1) <a href="https://researchtrend.ai/papers/2410.12601" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
(2) CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
🔍 More at researchtrend.ai/communities/CoGe
July 22, 2025 at 3:09 AM
[2025-07-22] 📚 Updates in #CoGe
(1) <a href="https://researchtrend.ai/papers/2410.12601" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
(2) CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
🔍 More at researchtrend.ai/communities/CoGe
(1) <a href="https://researchtrend.ai/papers/2410.12601" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
(2) CCSBench: Evaluating Compositional Controllability in LLMs for Scientific Document Summarization
🔍 More at researchtrend.ai/communities/CoGe
with user queries. The guidance module integrates an LLM-based Chain-of-Thought (CoT) code generator and an LLM-based code debugger, enhancing the controllability and robustness in generating guidance functions. Extensive experiments conducted on the [5/7 of https://arxiv.org/abs/2505.11247v1]
May 19, 2025 at 6:00 AM
with user queries. The guidance module integrates an LLM-based Chain-of-Thought (CoT) code generator and an LLM-based code debugger, enhancing the controllability and robustness in generating guidance functions. Extensive experiments conducted on the [5/7 of https://arxiv.org/abs/2505.11247v1]
Fritz Colonius, Alexandre J. Santana: Global controllability properties of linear control systems https://arxiv.org/abs/2505.01063 https://arxiv.org/pdf/2505.01063 https://arxiv.org/html/2505.01063
May 5, 2025 at 6:05 AM
Fritz Colonius, Alexandre J. Santana: Global controllability properties of linear control systems https://arxiv.org/abs/2505.01063 https://arxiv.org/pdf/2505.01063 https://arxiv.org/html/2505.01063
Marco Peruzzo, Giacomo Baggio, Francesco Ticozzi
Obtaining Structural Network Controllability with Higher-Order Local Dynamics
https://arxiv.org/abs/2504.17417
Obtaining Structural Network Controllability with Higher-Order Local Dynamics
https://arxiv.org/abs/2504.17417
April 25, 2025 at 5:40 AM
Marco Peruzzo, Giacomo Baggio, Francesco Ticozzi
Obtaining Structural Network Controllability with Higher-Order Local Dynamics
https://arxiv.org/abs/2504.17417
Obtaining Structural Network Controllability with Higher-Order Local Dynamics
https://arxiv.org/abs/2504.17417
📚 New Arxiv Paper
Title: Exact Controllability for a Refined Stochastic Hyperbolic Equation with Internal Controls
Authors: Zengyu Li, Zhonghua Liao, Qi L\"u
Read more: https://arxiv.org/abs/2504.09262
Title: Exact Controllability for a Refined Stochastic Hyperbolic Equation with Internal Controls
Authors: Zengyu Li, Zhonghua Liao, Qi L\"u
Read more: https://arxiv.org/abs/2504.09262
April 15, 2025 at 8:04 AM
📚 New Arxiv Paper
Title: Exact Controllability for a Refined Stochastic Hyperbolic Equation with Internal Controls
Authors: Zengyu Li, Zhonghua Liao, Qi L\"u
Read more: https://arxiv.org/abs/2504.09262
Title: Exact Controllability for a Refined Stochastic Hyperbolic Equation with Internal Controls
Authors: Zengyu Li, Zhonghua Liao, Qi L\"u
Read more: https://arxiv.org/abs/2504.09262
Structural and functional features characterizing the brains of individuals with higher controllability of motor imagery https://www.biorxiv.org/content/10.1101/2023.10.11.560970v1
Structural and functional features characterizing the brains of individuals with higher controllability of motor imagery https://www.biorxiv.org/content/10.1101/2023.10.11.560970v1
Motor imagery is a higher-order cognitive brain function that mentally simulates movements without p
www.biorxiv.org
October 16, 2023 at 5:20 PM
Structural and functional features characterizing the brains of individuals with higher controllability of motor imagery https://www.biorxiv.org/content/10.1101/2023.10.11.560970v1
📚 New Arxiv Paper
Title: Carleman estimate for semi-discrete stochastic parabolic operators in arbitrary dimension and applications to controllability
Authors: Rodrigo Lecaros, Ariel A. P\'erez, Manuel F. Prado
Read more: https://arxiv.org/abs/2503.03596
Title: Carleman estimate for semi-discrete stochastic parabolic operators in arbitrary dimension and applications to controllability
Authors: Rodrigo Lecaros, Ariel A. P\'erez, Manuel F. Prado
Read more: https://arxiv.org/abs/2503.03596
March 6, 2025 at 8:04 AM
📚 New Arxiv Paper
Title: Carleman estimate for semi-discrete stochastic parabolic operators in arbitrary dimension and applications to controllability
Authors: Rodrigo Lecaros, Ariel A. P\'erez, Manuel F. Prado
Read more: https://arxiv.org/abs/2503.03596
Title: Carleman estimate for semi-discrete stochastic parabolic operators in arbitrary dimension and applications to controllability
Authors: Rodrigo Lecaros, Ariel A. P\'erez, Manuel F. Prado
Read more: https://arxiv.org/abs/2503.03596
with an average 17.06\% accuracy gain across four benchmarks while exhibiting a strong adaptation capability to novel preferences, robustness to limited user data, and precise preference controllability. These results validate our framework's [5/6 of https://arxiv.org/abs/2503.15463v1]
March 20, 2025 at 5:59 AM
with an average 17.06\% accuracy gain across four benchmarks while exhibiting a strong adaptation capability to novel preferences, robustness to limited user data, and precise preference controllability. These results validate our framework's [5/6 of https://arxiv.org/abs/2503.15463v1]
billions-of-parameter LLMs and maintains controllability. Through extensive experiments across seven language tasks, four vision tasks, and three multimodal tasks using five pre-trained LLMs, we demonstrate that $\texttt{ORAL}$ generates high-quality [5/6 of https://arxiv.org/abs/2503.24354v1]
April 1, 2025 at 6:26 AM
billions-of-parameter LLMs and maintains controllability. Through extensive experiments across seven language tasks, four vision tasks, and three multimodal tasks using five pre-trained LLMs, we demonstrate that $\texttt{ORAL}$ generates high-quality [5/6 of https://arxiv.org/abs/2503.24354v1]