#toppaper — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #toppaper, aggregated by home.social.
-
NEW BIML Bibliography entry
https://arxiv.org/abs/2606.03811
AI Agents Enable Adaptive Computer Worms
Guan, Jonas, Tom Blanchard, Hanna Foerster, Hengrui Jia, Gabriel Huang, and Nicolas Papernot
This paper is a clarion call. Time to wake up! Papernot at his best, reminding us why Machine Learning Security is crucially important. See our blog entry Echoes of the Morris Wake-up Call of 1988: https://berryvilleiml.com/2026/06/03/echoes-of-the-morris-wake-up-call-of-1988/
-
NEW BIML Bibliography entry
https://arxiv.org/abs/2507.19457
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Agrawal, Lakshya A., et al
This is an important paper moving toward the idea of agentic harnesses. There are better ways to do this, but organizing and improving harnesses is a real thing.
-
NEW BIML Bibliography entry
https://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.
-
NEW BIML Bibliography entry
https://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?
-
NEW BIML Bibliography entry
https://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.
-
NEW BIML Bibliography entry
https://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.
-
NEW BIML Bibliography entry
https://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 -
NEW BIML Bibliography entry
https://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.
-
NEW BIML Bibliography entry AND NEW TOP FIVE #MLsec PAPER
READ IT
https://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.
-
NEW BIML Bibliography entry
https://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.
-
NEW BIML Bibliography entry
https://www.nature.com/articles/s41586-025-09446-5
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.
-
NEW BIML Bibliography entry
https://direct.mit.edu/books/oa-monograph/5600/Context-Changes-EverythingHow-Constraints-Create
Chapter 13, Context Changes Everything
Alicia Juarrero
A solid treatment of the 4Es theory (Embodied, Embedded, Extended, Enactive) properly grounded in philosophy of mind.
-
NEW BIML Bibliography entry
https://bpb-us-w2.wpmucdn.com/web.sas.upenn.edu/dist/7/206/files/2016/09/37cogucs76pap-1br5n10.pdf
The Evolution of Intelligence and Access to Cognitive Unconscious
Paul Rozin
Social learning, tool use, and psychology. An ancient and still relevant paper. Discusses evolution and genetic programming.
-
NEW BIML Bibliography entry
https://arxiv.org/abs/2506.21521v1
Potemkin Understanding in Large Language Models
Marina Mancoridis et al
Consistency checks demonstrate the paucity of LLM "concepts." Error-making in systems reveals important issues. This work rediscovers something important and introduces some new nomenclature for describing it.
-
NEW BIML Bibliography entry
https://arxiv.org/abs/2505.11581
Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis
Akarsh Kumar et al
Excellent work on representation in the face of stochastic gradient descent. This is a top paper in representation. Introduces FER. Toward creativity and intuition.