Login
Tree Search Distillation for Language Models Using PPO
(ayushtambde.com) by at2005 | view | 2 comments
Google identifies over 100k prompts used in distillation attacks
(cloud.google.com) by carterpeterson | view | 4 comments
Anthropic: Industrial-scale distillation attacks on our models by Chinese AI
(twitter.com) by mudil | view | 1 comments
CausalWan-Moe Preview: Applying Self-Forcing Distillation to Wan2.2
(hao-ai-lab.github.io) by wlsaidhi | view | 0 comments
Fair Use Paradox: Training and Distillation
(jasonwillems.com) by jayw_lead | view | 0 comments
Alleged Distillation Attacks by DeepSeek, Moonshot AI, and MiniMax
(twitter.com) by mike_kamau | view | 0 comments
Anthropic announces proof of distillation at scale by MiniMax, DeepSeek,Moonshot
(twitter.com) by Jimmc414 | view | 0 comments
Generalized On-Policy Distillation with Reward Extrapolation
(arxiv.org) by fzliu | view | 0 comments
Show HN: Symbolic Circuit Distillation: prove program to LLM circuit equivalence
(github.com) by nsomani | view | 0 comments
Fair Use Paradox: If Training on Public Data Is Fair Use, Why Not Distillation?
(jasonwillems.com) by jayw_lead | view | 1 comments
Feedback Alignment in Self-Distillation
(arxiv.org) by MediaSquirrel | view | 0 comments
OPRD: On-Policy Representation Distillation
(arxiv.org) by berlianta | view | 0 comments
Skill Distillation
(tomtunguz.com) by walterbell | view | 0 comments
On-Policy Distillation
(paperswithcode.co) by gmays | view | 0 comments
Self-distillation for training models on production traces
(trajectory.ai) by neilkale | view | 0 comments
Self-Distillation Enables Continual Learning [PDF]
(arxiv.org) by teleforce | view | 0 comments
SFT, RL, and On-Policy Distillation Through a Distributional Lens
(nrehiew.github.io) by gmays | view | 0 comments
On-Policy [LLM] Distillation
(thinkingmachines.ai) by nateb2022 | view | 0 comments
The Distillation Panic
(interconnects.ai) by pretext | view | 0 comments
Anthropic's anti-distillation defense,reverse-engineered from Claude Code source
(wanlanglin.github.io) by felixwll | view | 1 comments
I over-engineered my simple AI back end: distillation, router, embedding etc.
(sisyphusconsulting.org) by bhagyeshsp | view | 1 comments
US accuses China of industrial-scale AI model distillation, will share Intel
(thenextweb.com) by gmays | view | 0 comments
The West Talks About "Distillation." Fine. Let's Talk About Project Azorian
(valeman.medium.com) by ibobev | view | 0 comments
When model distillation becomes a diplomatic incident
(underlines.news) by dtedesco1 | view | 0 comments
White House Memo on Adversarial Distillation of American AI Models [pdf]
(whitehouse.gov) by lebovic | view | 0 comments
Whitehouse memo on Adversarial Distillation [pdf]
(whitehouse.gov) by vibe42 | view | 0 comments
Compressing LLMs with progressive pruning and multi-objective distillation
(rig.ai) by adam_patarino | view | 1 comments
Adversarial distillation
(frontiermodelforum.org) by hhs | view | 0 comments
Anti-Distillation for Employee Skills
(github.com) by mooreds | view | 0 comments
Anthropic, OpenAI and Google sharing Intel to block Chinese distillation
(bloomberg.com) by nikcub | view | 0 comments
Apple: Embarrassingly Simple Self-Distillation Improves Code Generation
(arxiv.org) by Anon84 | view | 0 comments
Embarrassingly Simple Self-Distillation Improves Code Generation
(arxiv.org) by jryio | view | 0 comments
Simple Self-Distillation
(github.com) by mihau | view | 0 comments
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL, On-Policy Distillation
(arxiv.org) by gmays | view | 0 comments
Mathematics Distillation Challenge – Equational Theories
(terrytao.wordpress.com) by picafrost | view | 0 comments
When Distillation Strips the Soul: Safety Comparison of a Claude-Distilled Model
(netrork.com) by jrork | view | 0 comments
Show HN: Aside – Local meeting capture with vault-native AI distillation
(github.com) by jphorism | view | 0 comments
The Distillation Problem, It's Not a Cold War, It's Napster
(stickybit.com.br) by TiMagazine | view | 0 comments
Antidistillation for AI Openess
(antidistillation.com) by rvttt | view | 0 comments
Antidistillation preserves AI openness, originality, and safety
(antidistillation.com) by umairnadeem123 | view | 0 comments
Anthropic could be exaggerating about the distillation efforts of Chinese labs [video]
(youtube.com) by logicprog | view | 0 comments
Anthropic joins OpenAI in flagging distillation campaigns by Chinese AI firms
(cnbc.com) by seydor | view | 0 comments
Detecting and Preventing Distillation Attacks
(anthropic.com) by meetpateltech | view | 0 comments
In Forecasting, Search >> Distillation
(spylab.ai) by polymorph1sm | view | 0 comments
GTIG AI Threat Tracker: Distillation, Experimentation, Adversarial Use
(cloud.google.com) by thread_id | view | 0 comments
Retrieval-Aware Distillation for Transformer-SSM Hybrids
(arxiv.org) by readitalready | view | 0 comments
Distillation, Experimentation, and Integration of AI for Adversarial Use
(cloud.google.com) by nsoonhui | view | 0 comments
Quantization-Aware Distillation
(ternarysearch.blogspot.com) by paladin314159 | view | 0 comments
Quantization-Aware Distillation for NVFP4 Inference Accuracy Recovery [pdf]
(research.nvidia.com) by gmays | view | 0 comments
Self-Distillation Enables Continual Learning
(arxiv.org) by simonpure | view | 0 comments