AI Post Transformers

mcgrof
  • 3.7 (3)
  • Technology
  • Updated Daily

AI-generated podcast where hosts Hal Turing and Dr. Ada Shannon discuss the latest research papers and reports in machine learning, AI systems, and optimization. Featuring honest critical analysis, proper citations, and nerdy humor.

  1. 1d ago

    Recursive Self-Improvement and Alignment: OpenAI's "An Alien Mind"

    This episode examines "An Alien Mind," a single-author essay from an OpenAI research leader arguing that internal results point toward sustained progress and eventually recursive self-improvement, and asks what an outside reader could actually verify. The hosts note that the essay offers no methods, tables, or error bars. They contrast its scaling claims with quantitative work like the Kaplan and Hoffmann scaling-law papers, which give fitted curves and exponents. They also discuss the essay's admission that easy-to-measure capabilities improve faster than hard-to-quantify ones, which makes progress harder to gauge. A large part of the discussion covers how the essay defines alignment: goal alignment versus value alignment, and whether that split is a real testable distinction or a blurry one. The hosts also introduce chain-of-thought monitoring, its fragility when reasoning is trained to look good, and safety cases as a basis for mandated bars. Listeners get a skeptical, evidence-focused look at what a lab insider's claims about AI progress and safety would need in order to hold up. Sources: 1. Recursive Self-Improvement and Alignment: OpenAI's "An Alien Mind" https://openai.com/index/an-alien-mind/ 2. Artificial Intelligence, Values, and Alignment — Iason Gabriel, 2020 https://scholar.google.com/scholar?q=Artificial+Intelligence%2C+Values%2C+and+Alignment 3. Training language models to follow instructions with human feedback (InstructGPT) — Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, et al. (OpenAI), 2022 https://scholar.google.com/scholar?q=Training+language+models+to+follow+instructions+with+human+feedback+%28InstructGPT%29 4. The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions — Eric Wallace, Kai Xiao, Reimar Leike, Lilian Weng, Johannes Heidecke, Alex Beutel (OpenAI), 2024 https://scholar.google.com/scholar?q=The+Instruction+Hierarchy%3A+Training+LLMs+to+Prioritize+Privileged+Instructions 5. Emergent Misalignment: Narrow Finetuning Can Produce Broadly Misaligned LLMs — Jan Betley, Daniel Tan, Niels Warncke, Anna Sztyber-Betley, Xuchan Bao, Martín Soto, Nathan Labenz, Owain Evans, 2025 https://scholar.google.com/scholar?q=Emergent+Misalignment%3A+Narrow+Finetuning+Can+Produce+Broadly+Misaligned+LLMs 6. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety — Korbak et al. (multi-lab position paper), 2025 https://scholar.google.com/scholar?q=Chain+of+Thought+Monitorability%3A+A+New+and+Fragile+Opportunity+for+AI+Safety 7. Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation — Baker et al. (OpenAI), 2025 https://scholar.google.com/scholar?q=Monitoring+Reasoning+Models+for+Misbehavior+and+the+Risks+of+Promoting+Obfuscation 8. Clarifying AI alignment — Paul Christiano, 2018 https://scholar.google.com/scholar?q=Clarifying+AI+alignment 9. Deep Reinforcement Learning from Human Preferences — Christiano, Leike, Brown, Martic, Legg, Amodei, 2017 https://scholar.google.com/scholar?q=Deep+Reinforcement+Learning+from+Human+Preferences 10. Alignment Faking in Large Language Models — Greenblatt et al. (Anthropic and Redwood Research), 2024 https://scholar.google.com/scholar?q=Alignment+Faking+in+Large+Language+Models 11. The Persona Selection Model — Anthropic, 2026 https://scholar.google.com/scholar?q=The+Persona+Selection+Model 12. Goal Misgeneralization in Deep Reinforcement Learning — Langosco, Koch, Sharkey, Pfau, Krueger, 2022 https://scholar.google.com/scholar?q=Goal+Misgeneralization+in+Deep+Reinforcement+Learning 13. Risks from Learned Optimization in Advanced Machine Learning Systems — Hubinger, van Merwe, Mikulik, Skalse, Garrabrant, 2019 https://scholar.google.com/scholar?q=Risks+from+Learned+Optimization+in+Advanced+Machine+Learning+Systems 14. Weak-to-Strong Generalization: Eliciting Strong Capabilities with Weak Supervision — Burns et al. (OpenAI), 2023 https://scholar.google.com/scholar?q=Weak-to-Strong+Generalization%3A+Eliciting+Strong+Capabilities+with+Weak+Supervision 15. Training Language Models to Self-Report / Confessions — OpenAI Alignment team, 2025-2026 https://scholar.google.com/scholar?q=Training+Language+Models+to+Self-Report+%2F+Confessions Interactive Visualization: Recursive Self-Improvement and Alignment: OpenAI's "An Alien Mind"

  2. 2d ago

    CacheBridge: Fixing Cross-Model KV Cache Transfer Failures

    This episode examines CacheBridge, a paper proposing targeted fixes to a training-free method for transferring KV caches between different transformer models in multi-model routing setups. It explains why caches can't simply be handed off — differing residual widths, GQA head counts, and RoPE position encoding make one model's cache unreadable to another — and how a prior affine-mapper approach (FULL-HEADMAPPING) could swing wildly from near-native accuracy on one model pair to catastrophic collapse on another, with no way to predict which. The discussion breaks down the paper's four diagnosed failure causes, spanning head-mixing, mismatched error metrics, layer-count cost scaling, and a GPU implementation bottleneck, then covers the three corresponding repairs: HEAD-LOCAL's narrower one-to-one head mapping, ATTN-REPAIR's attention-aware calibration reweighting, and FUSED-FIT's custom kernel for building the mapper efficiently. Listeners interested in LLM serving infrastructure will find it a concrete look at diagnosing and patching a deployed technique rather than proposing a new architecture from scratch. Sources: 1. CacheBridge: Efficient Cross-Model KV Cache Transfer — Xingyu Qu, Siyuan Lu, Zhiyu Chen, Sheng Wang, Tao Lin, 2026 http://arxiv.org/abs/2609.00891 2. Cross-model KV cache transfer in LLM families: A closed-form linear mapping for prefill reuse — Heo, T., Shafipour, R., Zhao, R., Golub, M., Kamani, M. M., Borkar, R., Chandran, M. T., Zardoshti, P., Rouhani, B. D., 2026 https://scholar.google.com/scholar?q=Cross-model+KV+cache+transfer+in+LLM+families%3A+A+closed-form+linear+mapping+for+prefill+reuse 3. Cache-to-cache: Direct semantic communication between large language models — Fu, T., Min, Z., Zhang, H., Yan, J., Dai, G., Ouyang, W., Wang, Y., 2026 https://scholar.google.com/scholar?q=Cache-to-cache%3A+Direct+semantic+communication+between+large+language+models 4. Mixture-of-translators: Translating KV caches across heterogeneous large language models — Lee, J.-w., Song, M., Oh, J., Han, S., Park, S., Jang, G., Lim, S., 2026 https://scholar.google.com/scholar?q=Mixture-of-translators%3A+Translating+KV+caches+across+heterogeneous+large+language+models 5. DroidSpeak: KV cache sharing across fine-tuned model variants — Liu, Y., Huang, Y., Yao, J., Feng, S., Gu, Z., Du, K., Li, H., Cheng, Y., Jiang, J., Lu, S., Musuvathi, M., Choukse, E., 2026 https://scholar.google.com/scholar?q=DroidSpeak%3A+KV+cache+sharing+across+fine-tuned+model+variants 6. ICaRus: Identical cache reuse for efficient multi model inference — Woo, S., Kil, J., Kim, H., Kim, M., Kim, J., Seo, A., Lee, S., Jo, M., Ryu, J., Park, B., Kwon, S. J., Lee, D., 2026 https://scholar.google.com/scholar?q=ICaRus%3A+Identical+cache+reuse+for+efficient+multi+model+inference 7. GQA: Training generalized multi-query transformer models from multi-head checkpoints — Ainslie, J., Lee-Thorp, J., de Jong, M., Zemlyanskiy, Y., Lebrón, F., Sanghai, S., 2023 https://scholar.google.com/scholar?q=GQA%3A+Training+generalized+multi-query+transformer+models+from+multi-head+checkpoints Interactive Visualization: CacheBridge: Fixing Cross-Model KV Cache Transfer Failures

  3. 2d ago

    Cross-Model KV Cache Transfer for Fast LLM Prefill Reuse

    This episode examines a NVIDIA paper on transferring KV cache between different-sized models within the same architecture family — for example Qwen3 14B and 32B — without any gradient training. The hosts explain the core finding: a single layer of a smaller model's cache can explain over half the variance in a larger model's keys, and stacking source layers pushes that correlation even higher. They break down the two practical payoffs — using a small model's cache to bootstrap a larger model mid-conversation for quality upgrades, and the reverse direction, prefilling once on an expensive large model then handing the cache down to a cheap model to skip decode costs entirely. A skeptical exchange probes whether a closed-form ridge-regression mapping can really generalize across the nonlinear depth of transformer layers, with the paper's authors measuring rather than assuming the linear structure holds, and only for "matched-KV pairs" with identical head counts and per-head dimensions. Listeners interested in inference cost reduction, model routing, and cache reuse across model families will find the comparison to trained alternatives like Cache-to-cache and LatentAlign particularly relevant. Sources: 1. Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse — Taekyung Heo, Rasoul Shafipour, Ritchie Zhao, Maximilian Golub, Mohammad Mahdi Kamani, Ritika Borkar, Makesh Tarun Chandran, Pantea Zardoshti, Bita Darvish Rouhani, 2026 http://arxiv.org/abs/2608.03893 2. Cache-to-cache: Direct semantic communication between large language models (C2C) — Tianyu Fu, Zihan Min, Hanling Zhang, Jichao Yan, Guohao Dai, Wanli Ouyang, Yu Wang, 2026 (ICLR) https://scholar.google.com/scholar?q=Cache-to-cache%3A+Direct+semantic+communication+between+large+language+models+%28C2C%29 3. Latent space communication via K-V cache alignment (LatentAlign) — Lucio M. Dery, Zohar Yahav, Henry Prior, Qixuan Feng, Jiajun Shen, Arthur Szlam, 2026 https://scholar.google.com/scholar?q=Latent+space+communication+via+K-V+cache+alignment+%28LatentAlign%29 4. DroidSpeak: KV cache sharing across fine-tuned model variants — Yuhan Liu et al., 2026 (NSDI) https://scholar.google.com/scholar?q=DroidSpeak%3A+KV+cache+sharing+across+fine-tuned+model+variants 5. The Platonic Representation Hypothesis — Minyoung Huh, Brian Cheung, Tongzhou Wang, Phillip Isola, 2024 (ICML) https://scholar.google.com/scholar?q=The+Platonic+Representation+Hypothesis 6. Nvidia Nemotron 3: Efficient and open intelligence — Aaron Blakeman et al., 2025 https://scholar.google.com/scholar?q=Nvidia+Nemotron+3%3A+Efficient+and+open+intelligence Interactive Visualization: Cross-Model KV Cache Transfer for Fast LLM Prefill Reuse

  4. 2d ago

    Dream-RSI: Teaching AI How to Search, Not Just Solve

    This episode examines "Dream-RSI: Recursive Self-Improvement through Evolving Worlds," which proposes making the exploration strategy of a discovery system — not the underlying model — the target of recursive self-improvement. Rather than optimizing candidate solutions directly, the system optimizes the policy that decides how to search: which branches to expand, how to parallelize workers, and when to stop, while the underlying coding agent (Gemini, in the paper's experiments) stays fixed. The key innovation is "dreaming": replaying an already-recorded discovery tree of past generate-evaluate attempts as a cheap simulator, letting new exploration policies be scored for free against historical outcomes instead of running costly new agent calls. This produces a three-stage loop — online exploration to grow the tree, constructing a replay simulator from it, then "dreaming" to test and select better policies before redeploying them — addressing the classic problem that policy-level exploration research suffers from painfully delayed feedback. The discussion situates the work against prior exploration methods like bandit algorithms, RL², Never Give Up, and FunSearch, making it a useful listen for anyone interested in how search-strategy meta-optimization, rather than raw model capability, might be the next lever for scaling AI-driven discovery. Sources: 1. Dream-RSI: Recursive Self-Improvement through Evolving Worlds — Tong Zheng, Xidong Wu, Zheng Zhang, Zhankui He, Chaoyi Zhang, Benjamin Coleman, Ruoqiao Wei, Di Bai, Haolin Liu, Rui Liu, Xue Wang, Yue Zhuan, Wang-Cheng Kang, Renkai Xiang, Heng Huang, Xinwu Cheng, Yunsong Guo, 2026 http://arxiv.org/abs/2609.14858 2. RL²: Fast Reinforcement Learning via Slow Reinforcement Learning — Yan Duan, John Schulman, Xi Chen, Peter L. Bartlett, Ilya Sutskever, Pieter Abbeel, 2016 https://scholar.google.com/scholar?q=RL%C2%B2%3A+Fast+Reinforcement+Learning+via+Slow+Reinforcement+Learning 3. Never Give Up: Learning Directed Exploration Strategies — Adrià Puigdomènech Badia, Pablo Sprechmann, Alex Vitvitskyi, et al. (DeepMind), 2020 https://scholar.google.com/scholar?q=Never+Give+Up%3A+Learning+Directed+Exploration+Strategies 4. Mathematical discoveries from program search with large language models (FunSearch) — Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, et al. (Google DeepMind), 2024 https://scholar.google.com/scholar?q=Mathematical+discoveries+from+program+search+with+large+language+models+%28FunSearch%29 5. Taking the Human Out of the Loop: A Review of Bayesian Optimization — Bobak Shahriari, Kevin Swersky, Ziyu Wang, Ryan P. Adams, Nando de Freitas, 2016 https://scholar.google.com/scholar?q=Taking+the+Human+Out+of+the+Loop%3A+A+Review+of+Bayesian+Optimization 6. AlphaEvolve: A coding agent for scientific and algorithmic discovery — A. Novikov et al., 2025 https://scholar.google.com/scholar?q=AlphaEvolve%3A+A+coding+agent+for+scientific+and+algorithmic+discovery 7. Mastering diverse domains through world models (Dreamer V3) — D. Hafner, J. Pasukonis, J. Ba, T. Lillicrap, 2023 https://scholar.google.com/scholar?q=Mastering+diverse+domains+through+world+models+%28Dreamer+V3%29 8. EvoX: Meta-evolution for automated discovery — S. Liu et al., 2026 https://scholar.google.com/scholar?q=EvoX%3A+Meta-evolution+for+automated+discovery 9. Evaluation-driven scaling for scientific discovery (SimpleTES) — H. Ye et al., 2026 https://scholar.google.com/scholar?q=Evaluation-driven+scaling+for+scientific+discovery+%28SimpleTES%29 Interactive Visualization: Dream-RSI: Teaching AI How to Search, Not Just Solve

  5. 2d ago

    Latent Space Communication via K-V Cache Alignment

    This episode explores a Google DeepMind paper proposing that separately trained language models can exchange raw internal state — the key-value cache built during transformer inference — through a shared "global latent space," rather than communicating only through text. The hosts unpack why text is a lossy bottleneck for inter-model communication, and how lightweight, frozen-weight adapter pairs let each model translate its own cache into and out of this common space, keeping training cost linear rather than combinatorial as more models join the pool. A striking result anchors the discussion: translating a model's cache through this shared space can sometimes outperform the model's own untouched cache on the same task. The conversation connects this idea to familiar concepts like prefix-tuning and continuous latent reasoning, framing the cache exchange as a dynamic, evolving version of a static soft prompt. Listeners interested in how models might one day share "trains of thought" instead of finished sentences will find the tension between the approach's architectural simplicity and its surprising performance gains especially compelling. Sources: 1. Latent Space Communication via K-V Cache Alignment https://arxiv.org/pdf/2601.06123 2. Prefix-Tuning: Optimizing Continuous Prompts for Generation — Xiang Lisa Li, Percy Liang, 2021 https://scholar.google.com/scholar?q=Prefix-Tuning%3A+Optimizing+Continuous+Prompts+for+Generation 3. The Power of Scale for Parameter-Efficient Prompt Tuning — Brian Lester, Rami Al-Rfou, Noah Constant, 2021 https://scholar.google.com/scholar?q=The+Power+of+Scale+for+Parameter-Efficient+Prompt+Tuning 4. Relative Representations Enable Zero-Shot Latent Space Communication — Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Francesco Locatello, Emanuele Rodolà, 2022 https://scholar.google.com/scholar?q=Relative+Representations+Enable+Zero-Shot+Latent+Space+Communication 5. Git Re-Basin: Merging Models modulo Permutation Symmetries — Samuel K. Ainsworth, Jonathan Hayase, Siddhartha Srinivasa, 2022 https://scholar.google.com/scholar?q=Git+Re-Basin%3A+Merging+Models+modulo+Permutation+Symmetries 6. On the direct alignment of latent spaces — Lähner, Moeller, 2024 https://scholar.google.com/scholar?q=On+the+direct+alignment+of+latent+spaces 7. Harnessing the universal geometry of embeddings — Jha, Zhang, Shmatikov, Morris, 2025 https://scholar.google.com/scholar?q=Harnessing+the+universal+geometry+of+embeddings 8. Training Large Language Models to Reason in a Continuous Latent Space (Coconut) — Hao, Sukhbaatar, Su, Li, Hu, Weston, Tian, 2024 https://scholar.google.com/scholar?q=Training+Large+Language+Models+to+Reason+in+a+Continuous+Latent+Space+%28Coconut%29 9. DiPaCo: Distributed Path Composition — Douillard, Feng, Rusu, Kuncoro, Donchev, Chhaparia, Gog, Ranzato, Shen, Szlam, 2024 https://scholar.google.com/scholar?q=DiPaCo%3A+Distributed+Path+Composition Interactive Visualization: Latent Space Communication via K-V Cache Alignment

  6. 2d ago

    Mixture-of-Translators: Sharing KV Caches Across Different LLMs

    This episode examines "Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models" by Jin-woo Lee and six co-authors from Chungnam National University and KISTI, which tackles the problem of transferring one model's KV cache — its layer-by-layer key/value memory of a processed document — to a completely different model architecture without re-running the original text through it. The discussion explains why this is hard: a KV cache is shaped by the specific depth, width, and head count of the model that produced it, so naive copying fails and a learned "cache translation" is required instead. It surveys prior approaches (Cache-to-Cache, KVComm, Latent Space Communication, and Interlat) and their shared weakness — relying on a single universal mapping or shared latent space — before detailing how Mixture-of-Translators borrows the Mixture-of-Experts routing idea to assign different tokens to different specialized translator modules via a per-token gating network, paired with a Context Correction Loss to correct drift in the target model's own layers. Listeners interested in multi-agent LLM pipelines, cache-augmented generation, or reducing redundant prefill computation across heterogeneous model fleets will find the practical motivation and technical tradeoffs compelling, especially since the paper's honest partial-success framing offers more insight than a clean win would. Sources: 1. Mixture-of-Translators: Sharing KV Caches Across Different LLMs https://arxiv.org/pdf/2607.28979 2. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer — Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, Jeff Dean, 2017 https://scholar.google.com/scholar?q=Outrageously+Large+Neural+Networks%3A+The+Sparsely-Gated+Mixture-of-Experts+Layer 3. Relative Representations Enable Zero-Shot Latent Space Communication — Luca Moschella, Valentino Maiorca, Marco Fumero, Antonio Norelli, Francesco Locatello, Emanuele Rodolà, 2023 https://scholar.google.com/scholar?q=Relative+Representations+Enable+Zero-Shot+Latent+Space+Communication 4. Prompt Cache: Modular Attention Reuse for Low-Latency Inference — In Gim, Guojun Chen, Seung-seob Lee, Nikhil Sarda, Anurag Khandelwal, Lin Zhong, 2024 https://scholar.google.com/scholar?q=Prompt+Cache%3A+Modular+Attention+Reuse+for+Low-Latency+Inference 5. CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving — Yuhan Liu, Hanchen Li, Yihua Cheng, Siddhant Ray, Yuyang Huang, Qizheng Zhang, Kuntai Du, Jiayi Yao, Shan Lu, Ganesh Ananthanarayanan, Michael Maire, Henry Hoffmann, Ari Holtzman, Junchen Jiang, 2024 https://scholar.google.com/scholar?q=CacheGen%3A+KV+Cache+Compression+and+Streaming+for+Fast+Large+Language+Model+Serving 6. Cache-to-cache: Direct semantic communication between large language models — Tianyu Fu, Zihan Min, Hanling Zhang, Jichao Yan, Guohao Dai, Wanli Ouyang, Yu Wang, 2025 https://scholar.google.com/scholar?q=Cache-to-cache%3A+Direct+semantic+communication+between+large+language+models 7. KVComm: Enabling efficient LLM communication through selective KV sharing — Xiangyu Shi, Marco Chiesa, Gerald Q Maguire Jr, Dejan Kostic, 2025 https://scholar.google.com/scholar?q=KVComm%3A+Enabling+efficient+LLM+communication+through+selective+KV+sharing 8. Enabling agents to communicate entirely in latent space (Interlat) — Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Yu Cheng, Bo Zheng, Wei Chen, Haochao Ying, 2025 https://scholar.google.com/scholar?q=Enabling+agents+to+communicate+entirely+in+latent+space+%28Interlat%29 9. Latent space communication via KV cache alignment (LSC) — Lucio M Dery, Zohar Yahav, Henry Prior, Qixuan Feng, Jiajun Shen, Arthur Szlam, 2026 https://scholar.google.com/scholar?q=Latent+space+communication+via+KV+cache+alignment+%28LSC%29 10. Fast state restoration in LLM serving with HCache — Shiwei Gao, Youmin Chen, Jiwu Shu, 2025 https://scholar.google.com/scholar?q=Fast+state+restoration+in+LLM+serving+with+HCache Interactive Visualization: Mixture-of-Translators: Sharing KV Caches Across Different LLMs

  7. 4d ago

    Semantic Cache Distillation: Solving Semantic Drift in KV Cache Transfer

    This episode examines Semantic Cache Distillation, a technique for reusing KV caches across producer and consumer transformers that share architecture but have different fine-tuned weights. The discussion covers why prefill-decode disaggregation splits compute-bound and memory-bandwidth-bound phases across separate machines, and how naively shipping raw or compressed KV caches between differently-weighted models causes "semantic drift" — a small per-layer mismatch that compounds through deep residual networks and degrades generation quality. The hosts unpack the paper's REUSE mechanism, which uses paired producer-consumer KV traces and low-rank SVD factorization to build a shared latent code, letting a lightweight encoder-decoder pair reconstruct usable cache states instead of forcing a full recompute. Real-world motivations include LoRA-adapter fleets sharing a base model and draft-verifier pairs in speculative decoding. Listeners interested in LLM serving infrastructure will find the reported 2.65x time-to-first-token speedup, and the underlying cross-model cache reconstruction problem, a concrete look at an underexplored bottleneck in production inference systems. Sources: 1. Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching — Qianli Ma, Zhiqing Tang, Hanshuai Cui, Zhi Yao, Weijia Jia, 2026 http://arxiv.org/abs/2606.07684 2. S-LoRA: Serving Thousands of Concurrent LoRA Adapters — Ying Sheng, Shiyi Cao, Dacheng Li, Coleman Hooper, Nicholas Lee, Shuo Yang, Christopher Chou, Banghua Zhu, Lianmin Zheng, Kurt Keutzer, Joseph E. Gonzalez, Ion Stoica, 2024 https://scholar.google.com/scholar?q=S-LoRA%3A+Serving+Thousands+of+Concurrent+LoRA+Adapters 3. CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving — Yuhan Liu, Hanchen Li, Yihua Cheng, Siddhant Ray, Yuyang Huang, Qizheng Zhang, Kuntai Du, Jiayi Yao, Shan Lu, Ganesh Ananthanarayanan, Michael Maire, Henry Hoffmann, Ari Holtzman, Junchen Jiang, 2024 https://scholar.google.com/scholar?q=CacheGen%3A+KV+Cache+Compression+and+Streaming+for+Fast+Large+Language+Model+Serving 4. CacheBlend: Fast Large Language Model Serving with Cached Knowledge Fusion — Jiayi Yao, Hanchen Li, Yuhan Liu, Siddhant Ray, Yihua Cheng, Qizheng Zhang, Kuntai Du, Shan Lu, Junchen Jiang, 2024 https://scholar.google.com/scholar?q=CacheBlend%3A+Fast+Large+Language+Model+Serving+with+Cached+Knowledge+Fusion 5. Fast Inference from Transformers via Speculative Decoding — Yaniv Leviathan, Matan Kalman, Yossi Matias, 2023 https://scholar.google.com/scholar?q=Fast+Inference+from+Transformers+via+Speculative+Decoding 6. DroidSpeak: KV cache sharing for cross-LLM communication and multi-LLM serving — Liu, Y., Huang, Y., Yao, J., Feng, S., Gu, Z., Du, K., Li, H., Cheng, Y., Jiang, J., Lu, S., et al., 2024 https://scholar.google.com/scholar?q=DroidSpeak%3A+KV+cache+sharing+for+cross-LLM+communication+and+multi-LLM+serving 7. Cache-to-Cache: Direct semantic communication between large language models — Fu, T., Min, Z., Zhang, H., Yan, J., Dai, G., Ouyang, W., and Wang, Y., 2026 https://scholar.google.com/scholar?q=Cache-to-Cache%3A+Direct+semantic+communication+between+large+language+models 8. S-LoRA: Scalable serving of thousands of LoRA adapters — Sheng, Y., Cao, S., Li, D., Hooper, C., Lee, N., Yang, S., Chou, C., Zhu, B., Zheng, L., Keutzer, K., et al., 2024 https://scholar.google.com/scholar?q=S-LoRA%3A+Scalable+serving+of+thousands+of+LoRA+adapters 9. EAGLE: Speculative sampling requires rethinking feature uncertainty — Li, Y., Wei, F., Zhang, C., and Zhang, H., 2024 https://scholar.google.com/scholar?q=EAGLE%3A+Speculative+sampling+requires+rethinking+feature+uncertainty 10. Mooncake: A KVCache-centric disaggregated architecture for LLM serving — Qin, R., Li, Z., He, W., Zhang, M., Wu, Y., Zheng, W., and Xu, X., 2024 https://scholar.google.com/scholar?q=Mooncake%3A+A+KVCache-centric+disaggregated+architecture+for+LLM+serving Interactive Visualization: Semantic Cache Distillation: Solving Semantic Drift in KV Cache Transfer

  8. 5d ago

    Deep Drone Acrobatics: Vision-Only Zero-Shot Sim-to-Real Flight

    This episode explores "Deep Drone Acrobatics," which trains a quadrotor to fly extreme maneuvers — a Power Loop, Barrel Roll, and Matty Flip — using only an onboard camera and IMU, with no external motion capture. The discussion centers on how the policy is trained entirely in simulation via DAgger imitation learning, where a privileged model-predictive controller with perfect ground-truth state acts as an expert that a vision-limited student imitates, rather than through reinforcement learning or reward shaping. A key focus is the sim-to-real gap: at high accelerations, motion blur degrades vision-based state estimation, so the paper's "input abstraction" approach feeds the network geometry-based feature tracks instead of raw pixels, drawing on prior work showing that shared abstractions between simulated and real observations shrink the performance gap. The conversation also traces the paper's intellectual lineage, connecting it to "Does Computer Vision Matter for Action?" and "Learning by Cheating," while highlighting why acrobatic flight is a harder version of the sim-to-real problem than driving, since a flipping drone has no margin for hesitation. Listeners interested in robotics, sim-to-real transfer, or imitation learning will find a concrete, technically grounded case study of zero-shot policy transfer under extreme physical constraints. Sources: 1. Deep Drone Acrobatics: Vision-Only Zero-Shot Sim-to-Real Flight https://roboticsproceedings.org/rss16/p040.pdf 2. Learning by Cheating — Dian Chen, Brady Zhou, Vladlen Koltun, Philipp Krähenbühl, 2019 https://scholar.google.com/scholar?q=Learning+by+Cheating 3. Deep Drone Racing: From Simulation to Reality with Domain Randomization — Antonio Loquercio, Elia Kaufmann, René Ranftl, Alexey Dosovitskiy, Vladlen Koltun, Davide Scaramuzza, 2020 https://scholar.google.com/scholar?q=Deep+Drone+Racing%3A+From+Simulation+to+Reality+with+Domain+Randomization 4. Does computer vision matter for action? — Brady Zhou, Philipp Krähenbühl, Vladlen Koltun, 2019 https://scholar.google.com/scholar?q=Does+computer+vision+matter+for+action%3F 5. Driving Policy Transfer via Modularity and Abstraction — Matthias Müller, Alexey Dosovitskiy, Bernard Ghanem, Vladlen Koltun, 2018 https://scholar.google.com/scholar?q=Driving+Policy+Transfer+via+Modularity+and+Abstraction 6. Agile Autonomous Driving Using End-to-End Deep Imitation Learning — Yunpeng Pan, Ching-An Cheng, Kamil Saigol, Keuntaek Lee, Xinyan Yan, Evangelos Theodorou, Byron Boots, 2018 https://scholar.google.com/scholar?q=Agile+Autonomous+Driving+Using+End-to-End+Deep+Imitation+Learning 7. A reduction of imitation learning and structured prediction to no-regret online learning — Stéphane Ross, Geoffrey Gordon, Drew Bagnell, 2011 https://scholar.google.com/scholar?q=A+reduction+of+imitation+learning+and+structured+prediction+to+no-regret+online+learning Interactive Visualization: Deep Drone Acrobatics: Vision-Only Zero-Shot Sim-to-Real Flight

See All (892)

Ratings & Reviews

3.7
out of 5
3 Ratings

About

AI-generated podcast where hosts Hal Turing and Dr. Ada Shannon discuss the latest research papers and reports in machine learning, AI systems, and optimization. Featuring honest critical analysis, proper citations, and nerdy humor.

Information

You Might Also Like