home.social

#toppaper — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #toppaper, aggregated by home.social.

  1. NEW BIML Bibliography entry

    arxiv.org/pdf/2603.28052

    Meta-Harness: End-to-End Optimization of Model Harnesses

    Lee, Yoonho, Roshen Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, and Chelsea Finn

    Harnesses for Agentic AI include perception and memory devices that allow an LLM to externalize and preserve state. This work describes iterating over a set of harnesses and finding better ones. Results are impressive.

    #TOPPAPER #Agents #Engineering #LLM

    berryvilleiml.com/bibliography/

  2. NEW BIML Bibliography entry

    arxiv.org/pdf/2603.28052

    Meta-Harness: End-to-End Optimization of Model Harnesses

    Lee, Yoonho, Roshen Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, and Chelsea Finn

    Harnesses for Agentic AI include perception and memory devices that allow an LLM to externalize and preserve state. This work describes iterating over a set of harnesses and finding better ones. Results are impressive.

    #TOPPAPER #Agents #Engineering #LLM

    berryvilleiml.com/bibliography/

  3. NEW BIML Bibliography entry

    arxiv.org/pdf/2603.28052

    Meta-Harness: End-to-End Optimization of Model Harnesses

    Lee, Yoonho, Roshen Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, and Chelsea Finn

    Harnesses for Agentic AI include perception and memory devices that allow an LLM to externalize and preserve state. This work describes iterating over a set of harnesses and finding better ones. Results are impressive.

    #TOPPAPER #Agents #Engineering #LLM

    berryvilleiml.com/bibliography/

  4. NEW BIML Bibliography entry

    arxiv.org/pdf/2603.28052

    Meta-Harness: End-to-End Optimization of Model Harnesses

    Lee, Yoonho, Roshen Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, and Chelsea Finn

    Harnesses for Agentic AI include perception and memory devices that allow an LLM to externalize and preserve state. This work describes iterating over a set of harnesses and finding better ones. Results are impressive.

    #TOPPAPER #Agents #Engineering #LLM

    berryvilleiml.com/bibliography/

  5. NEW BIML Bibliography entry

    arxiv.org/pdf/2603.28052

    Meta-Harness: End-to-End Optimization of Model Harnesses

    Lee, Yoonho, Roshen Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, and Chelsea Finn

    Harnesses for Agentic AI include perception and memory devices that allow an LLM to externalize and preserve state. This work describes iterating over a set of harnesses and finding better ones. Results are impressive.

    #TOPPAPER #Agents #Engineering #LLM

    berryvilleiml.com/bibliography/

  6. NEW BIML Bibliography entry

    arxiv.org/abs/2512.24601

    Recursive Language Models

    Alex L. Zhang, Tim Kraska, Omar Khattab

    An excellent paper describing how to extend prompt context with recursion. Simple experiments. Clear explanations. This one makes you think. Are we moving towards actual Hofstaderian strange loops?

    #TOPPAPER #Engineering #LLM

    berryvilleiml.com/references/

  7. NEW BIML Bibliography entry

    arxiv.org/abs/2512.24601

    Recursive Language Models

    Alex L. Zhang, Tim Kraska, Omar Khattab

    An excellent paper describing how to extend prompt context with recursion. Simple experiments. Clear explanations. This one makes you think. Are we moving towards actual Hofstaderian strange loops?

    #TOPPAPER #Engineering #LLM

    berryvilleiml.com/references/

  8. NEW BIML Bibliography entry

    arxiv.org/abs/2512.24601

    Recursive Language Models

    Alex L. Zhang, Tim Kraska, Omar Khattab

    An excellent paper describing how to extend prompt context with recursion. Simple experiments. Clear explanations. This one makes you think. Are we moving towards actual Hofstaderian strange loops?

    #TOPPAPER #Engineering #LLM

    berryvilleiml.com/references/

  9. NEW BIML Bibliography entry

    arxiv.org/abs/2512.24601

    Recursive Language Models

    Alex L. Zhang, Tim Kraska, Omar Khattab

    An excellent paper describing how to extend prompt context with recursion. Simple experiments. Clear explanations. This one makes you think. Are we moving towards actual Hofstaderian strange loops?

    #TOPPAPER #Engineering #LLM

    berryvilleiml.com/references/

  10. NEW BIML Bibliography entry

    arxiv.org/abs/2512.24601

    Recursive Language Models

    Alex L. Zhang, Tim Kraska, Omar Khattab

    An excellent paper describing how to extend prompt context with recursion. Simple experiments. Clear explanations. This one makes you think. Are we moving towards actual Hofstaderian strange loops?

    #TOPPAPER #Engineering #LLM

    berryvilleiml.com/references/

  11. NEW BIML Bibliography entry

    arxiv.org/abs/2602.06923v1#

    From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers

    Ziming Liu, Sophia Sanborn, Surya Ganguli, Andreas Tolias

    Representation matters and is deeply constrained by tokenization. Excellent work, clearly described with real substance.

    #TOPPAPER #Representation #Tokenization

    berryvilleiml.com/references/

  12. NEW BIML Bibliography entry

    arxiv.org/abs/2602.06923v1#

    From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers

    Ziming Liu, Sophia Sanborn, Surya Ganguli, Andreas Tolias

    Representation matters and is deeply constrained by tokenization. Excellent work, clearly described with real substance.

    #TOPPAPER #Representation #Tokenization

    berryvilleiml.com/references/

  13. NEW BIML Bibliography entry

    arxiv.org/abs/2602.06923v1#

    From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers

    Ziming Liu, Sophia Sanborn, Surya Ganguli, Andreas Tolias

    Representation matters and is deeply constrained by tokenization. Excellent work, clearly described with real substance.

    #TOPPAPER #Representation #Tokenization

    berryvilleiml.com/references/

  14. NEW BIML Bibliography entry

    arxiv.org/abs/2602.06923v1#

    From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers

    Ziming Liu, Sophia Sanborn, Surya Ganguli, Andreas Tolias

    Representation matters and is deeply constrained by tokenization. Excellent work, clearly described with real substance.

    #TOPPAPER #Representation #Tokenization

    berryvilleiml.com/references/

  15. NEW BIML Bibliography entry

    arxiv.org/abs/2602.06923v1#

    From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers

    Ziming Liu, Sophia Sanborn, Surya Ganguli, Andreas Tolias

    Representation matters and is deeply constrained by tokenization. Excellent work, clearly described with real substance.

    #TOPPAPER #Representation #Tokenization

    berryvilleiml.com/references/

  16. NEW BIML Bibliography entry

    arxiv.org/abs/2503.03150

    Position: Model Collapse Does Not Mean What You Think

    Rylan Schaeffer, Joshua Kazdan, Alvan Caleb Arulandu, Sanmi Koyejo

    We think recursive pollution is a better term than model collapse. Weak terminology leads to misunderstanding of impact. See figure 4. This is a very good paper.

    #TOPPAPER #MLsec #RecursivePollution #DataPoisoning

    berryvilleiml.com/references/

  17. NEW BIML Bibliography entry

    arxiv.org/abs/2503.03150

    Position: Model Collapse Does Not Mean What You Think

    Rylan Schaeffer, Joshua Kazdan, Alvan Caleb Arulandu, Sanmi Koyejo

    We think recursive pollution is a better term than model collapse. Weak terminology leads to misunderstanding of impact. See figure 4. This is a very good paper.

    #TOPPAPER #MLsec #RecursivePollution #DataPoisoning

    berryvilleiml.com/references/

  18. NEW BIML Bibliography entry

    arxiv.org/abs/2503.03150

    Position: Model Collapse Does Not Mean What You Think

    Rylan Schaeffer, Joshua Kazdan, Alvan Caleb Arulandu, Sanmi Koyejo

    We think recursive pollution is a better term than model collapse. Weak terminology leads to misunderstanding of impact. See figure 4. This is a very good paper.

    #TOPPAPER #MLsec #RecursivePollution #DataPoisoning

    berryvilleiml.com/references/

  19. NEW BIML Bibliography entry

    arxiv.org/abs/2503.03150

    Position: Model Collapse Does Not Mean What You Think

    Rylan Schaeffer, Joshua Kazdan, Alvan Caleb Arulandu, Sanmi Koyejo

    We think recursive pollution is a better term than model collapse. Weak terminology leads to misunderstanding of impact. See figure 4. This is a very good paper.

    #TOPPAPER #MLsec #RecursivePollution #DataPoisoning

    berryvilleiml.com/references/

  20. NEW BIML Bibliography entry

    arxiv.org/abs/2503.03150

    Position: Model Collapse Does Not Mean What You Think

    Rylan Schaeffer, Joshua Kazdan, Alvan Caleb Arulandu, Sanmi Koyejo

    We think recursive pollution is a better term than model collapse. Weak terminology leads to misunderstanding of impact. See figure 4. This is a very good paper.

    #TOPPAPER #MLsec #RecursivePollution #DataPoisoning

    berryvilleiml.com/references/

  21. NEW BIML Bibliography entry

    arxiv.org/abs/2410.04840

    Strong Model Collapse

    Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian, Julia Kempe
    (NYU and META)

    Recursive pollution leads to model collapse. This view of strong model collapse describes what happens in the case of recursive data poison.
    #TOPPAPER #MLsec #Data #RecursivePollution

    berryvilleiml.com/references/

  22. NEW BIML Bibliography entry

    arxiv.org/abs/2410.04840

    Strong Model Collapse

    Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian, Julia Kempe
    (NYU and META)

    Recursive pollution leads to model collapse. This view of strong model collapse describes what happens in the case of recursive data poison.
    #TOPPAPER #MLsec #Data #RecursivePollution

    berryvilleiml.com/references/

  23. NEW BIML Bibliography entry

    arxiv.org/abs/2410.04840

    Strong Model Collapse

    Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian, Julia Kempe
    (NYU and META)

    Recursive pollution leads to model collapse. This view of strong model collapse describes what happens in the case of recursive data poison.
    #TOPPAPER #MLsec #Data #RecursivePollution

    berryvilleiml.com/references/

  24. NEW BIML Bibliography entry

    arxiv.org/abs/2410.04840

    Strong Model Collapse

    Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian, Julia Kempe
    (NYU and META)

    Recursive pollution leads to model collapse. This view of strong model collapse describes what happens in the case of recursive data poison.
    #TOPPAPER #MLsec #Data #RecursivePollution

    berryvilleiml.com/references/

  25. NEW BIML Bibliography entry

    arxiv.org/abs/2410.04840

    Strong Model Collapse

    Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian, Julia Kempe
    (NYU and META)

    Recursive pollution leads to model collapse. This view of strong model collapse describes what happens in the case of recursive data poison.
    #TOPPAPER #MLsec #Data #RecursivePollution

    berryvilleiml.com/references/

  26. NEW BIML Bibliography entry

    arxiv.org/abs/2509.16499

    A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

    Lianghe Shi, et al

    A very nice set of references to work in model collapse. Collapsed model == lookup table (that is, no generalization). Discussion of recursive pollution as causing variance shrinkage or distribution shift.

    #TOPPAPER #MLsec #Data #RecursivePollution

    berryvilleiml.com/references/

  27. NEW BIML Bibliography entry

    arxiv.org/abs/2509.16499

    A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

    Lianghe Shi, et al

    A very nice set of references to work in model collapse. Collapsed model == lookup table (that is, no generalization). Discussion of recursive pollution as causing variance shrinkage or distribution shift.

    #TOPPAPER #MLsec #Data #RecursivePollution

    berryvilleiml.com/references/

  28. NEW BIML Bibliography entry

    arxiv.org/abs/2509.16499

    A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

    Lianghe Shi, et al

    A very nice set of references to work in model collapse. Collapsed model == lookup table (that is, no generalization). Discussion of recursive pollution as causing variance shrinkage or distribution shift.

    #TOPPAPER #MLsec #Data #RecursivePollution

    berryvilleiml.com/references/

  29. NEW BIML Bibliography entry

    arxiv.org/abs/2509.16499

    A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

    Lianghe Shi, et al

    A very nice set of references to work in model collapse. Collapsed model == lookup table (that is, no generalization). Discussion of recursive pollution as causing variance shrinkage or distribution shift.

    #TOPPAPER #MLsec #Data #RecursivePollution

    berryvilleiml.com/references/

  30. NEW BIML Bibliography entry

    arxiv.org/abs/2509.16499

    A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

    Lianghe Shi, et al

    A very nice set of references to work in model collapse. Collapsed model == lookup table (that is, no generalization). Discussion of recursive pollution as causing variance shrinkage or distribution shift.

    #TOPPAPER #MLsec #Data #RecursivePollution

    berryvilleiml.com/references/

  31. NEW BIML Bibliography entry AND NEW TOP FIVE #MLsec PAPER

    READ IT

    arxiv.org/pdf/2510.07192

    Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

    Alexandra Souly, ... Nicholas Carlini, et al

    Excellent paper, clear and well-stated (like all Carlini papers). This result shows that recursive pollution risk is even greater than we thought. Injecting backdoors is pretty easy. The examples are a bit simplistic.

    #TOPPAPER #MLsec #Attacks #DataPoisoning

    berryvilleiml.com/references/

  32. NEW BIML Bibliography entry AND NEW TOP FIVE #MLsec PAPER

    READ IT

    arxiv.org/pdf/2510.07192

    Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

    Alexandra Souly, ... Nicholas Carlini, et al

    Excellent paper, clear and well-stated (like all Carlini papers). This result shows that recursive pollution risk is even greater than we thought. Injecting backdoors is pretty easy. The examples are a bit simplistic.

    #TOPPAPER #MLsec #Attacks #DataPoisoning

    berryvilleiml.com/references/

  33. NEW BIML Bibliography entry AND NEW TOP FIVE #MLsec PAPER

    READ IT

    arxiv.org/pdf/2510.07192

    Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

    Alexandra Souly, ... Nicholas Carlini, et al

    Excellent paper, clear and well-stated (like all Carlini papers). This result shows that recursive pollution risk is even greater than we thought. Injecting backdoors is pretty easy. The examples are a bit simplistic.

    #TOPPAPER #MLsec #Attacks #DataPoisoning

    berryvilleiml.com/references/

  34. NEW BIML Bibliography entry AND NEW TOP FIVE #MLsec PAPER

    READ IT

    arxiv.org/pdf/2510.07192

    Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

    Alexandra Souly, ... Nicholas Carlini, et al

    Excellent paper, clear and well-stated (like all Carlini papers). This result shows that recursive pollution risk is even greater than we thought. Injecting backdoors is pretty easy. The examples are a bit simplistic.

    #TOPPAPER #MLsec #Attacks #DataPoisoning

    berryvilleiml.com/references/

  35. NEW BIML Bibliography entry AND NEW TOP FIVE #MLsec PAPER

    READ IT

    arxiv.org/pdf/2510.07192

    Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

    Alexandra Souly, ... Nicholas Carlini, et al

    Excellent paper, clear and well-stated (like all Carlini papers). This result shows that recursive pollution risk is even greater than we thought. Injecting backdoors is pretty easy. The examples are a bit simplistic.

    #TOPPAPER #MLsec #Attacks #DataPoisoning

    berryvilleiml.com/references/

  36. NEW BIML Bibliography entry

    arxiv.org/abs/2510.04871

    Less is More: Recursive Reasoning with Tiny Networks

    Alexia Jolicoeur-Martineau

    This is an engineering exercise akin to “set it to 57,” but it is really interesting. A set of weekend kludges that has important implications. Harold wants to pursue this line to think about how integers are represented. Won the ARC prize.

    #TOPPAPER #Engineering #MLsec

    berryvilleiml.com/references/

  37. NEW BIML Bibliography entry

    arxiv.org/abs/2510.04871

    Less is More: Recursive Reasoning with Tiny Networks

    Alexia Jolicoeur-Martineau

    This is an engineering exercise akin to “set it to 57,” but it is really interesting. A set of weekend kludges that has important implications. Harold wants to pursue this line to think about how integers are represented. Won the ARC prize.

    #TOPPAPER #Engineering #MLsec

    berryvilleiml.com/references/

  38. NEW BIML Bibliography entry

    arxiv.org/abs/2510.04871

    Less is More: Recursive Reasoning with Tiny Networks

    Alexia Jolicoeur-Martineau

    This is an engineering exercise akin to “set it to 57,” but it is really interesting. A set of weekend kludges that has important implications. Harold wants to pursue this line to think about how integers are represented. Won the ARC prize.

    #TOPPAPER #Engineering #MLsec

    berryvilleiml.com/references/

  39. NEW BIML Bibliography entry

    arxiv.org/abs/2510.04871

    Less is More: Recursive Reasoning with Tiny Networks

    Alexia Jolicoeur-Martineau

    This is an engineering exercise akin to “set it to 57,” but it is really interesting. A set of weekend kludges that has important implications. Harold wants to pursue this line to think about how integers are represented. Won the ARC prize.

    #TOPPAPER #Engineering #MLsec

    berryvilleiml.com/references/

  40. NEW BIML Bibliography entry

    arxiv.org/abs/2510.04871

    Less is More: Recursive Reasoning with Tiny Networks

    Alexia Jolicoeur-Martineau

    This is an engineering exercise akin to “set it to 57,” but it is really interesting. A set of weekend kludges that has important implications. Harold wants to pursue this line to think about how integers are represented. Won the ARC prize.

    #TOPPAPER #Engineering #MLsec

    berryvilleiml.com/references/

  41. NEW BIML Bibliography entry

    nature.com/articles/s41586-025

    Optical generative models

    Chen, Shiqi, Yuhang Li, Yuntian Wang, Hanlong Chen and Aydogan Ozcan

    Light for computation with properties of low power and superposition. Analo of quantum computing. This reminds os of Rosenblatt’s Perceptrons from the ’50s.

    #TOPPAPER #MLsec #Engineering

    berryvilleiml.com/references/

  42. NEW BIML Bibliography entry

    nature.com/articles/s41586-025

    Optical generative models

    Chen, Shiqi, Yuhang Li, Yuntian Wang, Hanlong Chen and Aydogan Ozcan

    Light for computation with properties of low power and superposition. Analo of quantum computing. This reminds os of Rosenblatt’s Perceptrons from the ’50s.

    #TOPPAPER #MLsec #Engineering

    berryvilleiml.com/references/

  43. NEW BIML Bibliography entry

    nature.com/articles/s41586-025

    Optical generative models

    Chen, Shiqi, Yuhang Li, Yuntian Wang, Hanlong Chen and Aydogan Ozcan

    Light for computation with properties of low power and superposition. Analo of quantum computing. This reminds os of Rosenblatt’s Perceptrons from the ’50s.

    #TOPPAPER #MLsec #Engineering

    berryvilleiml.com/references/

  44. NEW BIML Bibliography entry

    nature.com/articles/s41586-025

    Optical generative models

    Chen, Shiqi, Yuhang Li, Yuntian Wang, Hanlong Chen and Aydogan Ozcan

    Light for computation with properties of low power and superposition. Analo of quantum computing. This reminds os of Rosenblatt’s Perceptrons from the ’50s.

    #TOPPAPER #MLsec #Engineering

    berryvilleiml.com/references/

  45. NEW BIML Bibliography entry

    nature.com/articles/s41586-025

    Optical generative models

    Chen, Shiqi, Yuhang Li, Yuntian Wang, Hanlong Chen and Aydogan Ozcan

    Light for computation with properties of low power and superposition. Analo of quantum computing. This reminds os of Rosenblatt’s Perceptrons from the ’50s.

    #TOPPAPER #MLsec #Engineering

    berryvilleiml.com/references/

  46. NEW BIML Bibliography entry

    direct.mit.edu/books/oa-monogr

    Chapter 13, Context Changes Everything

    Alicia Juarrero

    A solid treatment of the 4Es theory (Embodied, Embedded, Extended, Enactive) properly grounded in philosophy of mind.

    #MLsec #ML #TOPPAPER

    berryvilleiml.com/references/

  47. NEW BIML Bibliography entry

    direct.mit.edu/books/oa-monogr

    Chapter 13, Context Changes Everything

    Alicia Juarrero

    A solid treatment of the 4Es theory (Embodied, Embedded, Extended, Enactive) properly grounded in philosophy of mind.

    #MLsec #ML #TOPPAPER

    berryvilleiml.com/references/

  48. NEW BIML Bibliography entry

    direct.mit.edu/books/oa-monogr

    Chapter 13, Context Changes Everything

    Alicia Juarrero

    A solid treatment of the 4Es theory (Embodied, Embedded, Extended, Enactive) properly grounded in philosophy of mind.

    #MLsec #ML #TOPPAPER

    berryvilleiml.com/references/

  49. NEW BIML Bibliography entry

    direct.mit.edu/books/oa-monogr

    Chapter 13, Context Changes Everything

    Alicia Juarrero

    A solid treatment of the 4Es theory (Embodied, Embedded, Extended, Enactive) properly grounded in philosophy of mind.

    #MLsec #ML #TOPPAPER

    berryvilleiml.com/references/

  50. NEW BIML Bibliography entry

    direct.mit.edu/books/oa-monogr

    Chapter 13, Context Changes Everything

    Alicia Juarrero

    A solid treatment of the 4Es theory (Embodied, Embedded, Extended, Enactive) properly grounded in philosophy of mind.

    #MLsec #ML #TOPPAPER

    berryvilleiml.com/references/