x

75% of people globally want unbiased news (Pew Research) but are concerned they're not getting that.

Get balanced coverage with Symby. See how stories are covered across diverse outlets and spot when one side covers a story the other skips.

PODCAST

AI Post Transformers

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.

technology

All Episodes

00:55:27

Pre-computing & reusing KV caches to accelerate RAG...

AI Post Transformers ·

2025/09/18

How can pre-computing and reusing Key-Value (KV) caches accelerate inference for Retrieval-Augmented Generation and other long-context LLM tasks?The provided sources identify the same core problem—high latency in Large Language Model (LLM) inference due to processing long, repetitive contexts—and converge on a unified solution: leveraging pre-computed Key-Value (KV) caches. Each source then contributes a unique perspective on *how* to implement this solution effectively, addressing specific

en

00:08:08

REFRAG: Rethinking RAG-based Decoding

AI Post Transformers ·

2025/09/18

This September 2025 academic paper, titled "REFRAG: Rethinking RAG based Decoding," appears on the alphaXiv pre-print server. It focuses on Reframing Retrieval-Augmented Generation (RAG) within the context of decoding processes. The research likely explores new approaches or improvements to how RAG mechanisms are integrated and utilized during the generation of text. By "rethinking" this integration, the authors probably aim to optimize the performance or efficiency of language models that leverage

en

00:17:19

DeepSeek-R1: Reinforcing LLM Reasoning Through...

AI Post Transformers ·

2025/09/18

This paper published on Nature on September 17 2025, "DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning," details the development of DeepSeek-R1-Zero and DeepSeek-R1, two large language models (LLMs) engineered to enhance reasoning capabilities. The authors explain how reinforcement learning (RL) is used to enable emergent advanced reasoning patterns like self-reflection and dynamic strategy adaptation, moving beyond reliance on human-annotated data. The paper discusses

en

00:18:05

ShadowKV: High-Throughput Long-Context LLM Inference

AI Post Transformers ·

2025/09/17

This April 2025 paper introduces ShadowKV, an innovative inference system for long-context Large Language Models (LLMs) designed to significantly enhance throughput and support larger batch sizes without compromising accuracy. It achieves this by strategically managing the Key-Value (KV) cache: specifically, it compresses the low-rank pre-Rotary Position Embedding (RoPE) key cache on the GPU and offloads the value cache to the CPU. ShadowKV further optimizes performance through an accurate KV

en

00:18:00

TailorKV: Hybrid KV Cache Compression for LLMs

AI Post Transformers ·

2025/09/17

This May 2025 paper introduces TailorKV, a novel hybrid framework designed to optimize Key-Value (KV) cache management in large language models (LLMs) for long-context inference. It addresses challenges like high GPU memory consumption and inference latency that arise from the linear growth of KV cache size with sequence length. TailorKV categorizes Transformer layers into quantization-friendly and sparsity-friendly based on their attention patterns, applying 1-bit quantization to the former and

en

00:20:50

MIRAGE: Optimizing LLM KV Cache with Parameter Remapping

AI Post Transformers ·

2025/09/17

This July 2025 paper discusses advanced memory optimization techniques for Large Language Models (LLMs), particularly focusing on KV cache management in multi-tenant serving environments. The primary subject, MIRAGE, introduces parameter remapping, a novel method that dynamically repurposes GPU memory allocated for model parameters to expand KV cache capacity, outperforming traditional CPU-offloading and KV cache swapping by reducing latency and increasing throughput. Complementary research

en

00:19:36

WebSailor-V2: Bridging Proprietary Agents with...

AI Post Transformers ·

2025/09/17

This September 2025 paper introduces WebSailor-V2, an open-source deep research agent developed by Alibaba Group's Tongyi Lab. The paper details a post-training pipeline that uses a novel synthetic data construction scheme, SailorFog-QA-V2, and a dual-environment reinforcement learning framework. WebSailor-V2, built on the Qwen3-30B-A3B model, demonstrates state-of-the-art performance among open-source agents and is competitive with leading proprietary systems on various web-agent benchmarks,

en

00:25:08

Dynamic Chunking for Hierarchical Sequence Modeling

AI Post Transformers ·

2025/09/17

This July 2025 paper introduces Hierarchical Networks (H-Nets), a novel architecture designed to move beyond traditional tokenization in large language models by implementing dynamic chunking. This mechanism allows the model to automatically learn content- and context-dependent segmentation strategies directly from raw data, eliminating the need for predefined pre-processing steps like byte-pair encoding (BPE). H-Nets utilize a recursive, multi-stage structure that processes data at varying levels

en

00:17:01

LoFT: Parameter-Efficient Fine-Tuning for Long-tailed...

AI Post Transformers ·

2025/09/17

This September 2025 paper introduces LoFT, a novel framework designed to improve Long-Tailed Semi-Supervised Learning (LTSSL) by leveraging parameter-efficient fine-tuning of pre-trained foundation models. The core idea is to enhance confidence calibration and generate more reliable pseudo-labels, which are crucial for addressing the imbalance inherent in long-tailed datasets. Furthermore, the paper extends this approach to open-world scenarios with LoFT-OW, specifically incorporating mechanisms to

en

00:17:41

QuantAgent: Multi-Agent LLM for High-Frequency Trading

AI Post Transformers ·

2025/09/17

This September 2025 paper describes QuantAgent, a novel multi-agent large language model (LLM) framework designed for high-frequency quantitative trading based solely on price-derived market signals. The system decomposes trading decisions into four specialized agents—IndicatorAgent, PatternAgent, TrendAgent, and DecisionAgent—which analyze market dynamics from complementary perspectives and communicate through structured prompts. QuantAgent consistently outperforms baseline models across diverse

en

00:19:48

Infini-gram: Scaling Unbounded N-gram Language Models

AI Post Transformers ·

2025/09/17

This April 2025 paper introduces Infini-gram, a novel engine designed to scale n-gram language models to an unprecedented 5 trillion tokens and support unbounded n (∞-gram LMs). Unlike traditional methods that rely on pre-computed count tables, Infini-gram leverages suffix arrays for efficient, low-latency calculation of n-gram and ∞-gram probabilities, even for extremely long contexts. The authors demonstrate that this modernized approach significantly improves the perplexity of neural Large

en

ShadowKV: High-Throughput Long-Context LLM Inference

AI Post Transformers ·

2025/09/17

This April 2025 paper introduces ShadowKV, an innovative inference system for long-context Large Language Models (LLMs) designed to significantly enhance throughput and support larger batch sizes without compromising accuracy. It achieves this by strategically managing the Key-Value (KV) cache: specifically, it compresses the low-rank pre-Rotary Position Embedding (RoPE) key cache on the GPU and offloads the value cache to the CPU. ShadowKV further optimizes performance through an accurate KV

en

Dynamic Chunking for Hierarchical Sequence Modeling

AI Post Transformers ·

2025/09/17

This July 2025 paper introduces Hierarchical Networks (H-Nets), a novel architecture designed to move beyond traditional tokenization in large language models by implementing dynamic chunking. This mechanism allows the model to automatically learn content- and context-dependent segmentation strategies directly from raw data, eliminating the need for predefined pre-processing steps like byte-pair encoding (BPE). H-Nets utilize a recursive, multi-stage structure that processes data at varying levels

en

MIRAGE: Optimizing LLM KV Cache with Parameter Remapping

AI Post Transformers ·

2025/09/17

This July 2025 paper discusses advanced memory optimization techniques for Large Language Models (LLMs), particularly focusing on KV cache management in multi-tenant serving environments. The primary subject, MIRAGE, introduces parameter remapping, a novel method that dynamically repurposes GPU memory allocated for model parameters to expand KV cache capacity, outperforming traditional CPU-offloading and KV cache swapping by reducing latency and increasing throughput. Complementary research

en

TailorKV: Hybrid KV Cache Compression for LLMs

AI Post Transformers ·

2025/09/17

This May 2025 paper introduces TailorKV, a novel hybrid framework designed to optimize Key-Value (KV) cache management in large language models (LLMs) for long-context inference. It addresses challenges like high GPU memory consumption and inference latency that arise from the linear growth of KV cache size with sequence length. TailorKV categorizes Transformer layers into quantization-friendly and sparsity-friendly based on their attention patterns, applying 1-bit quantization to the former and

en

LoFT: Parameter-Efficient Fine-Tuning for Long-tailed...

AI Post Transformers ·

2025/09/17

This September 2025 paper introduces LoFT, a novel framework designed to improve Long-Tailed Semi-Supervised Learning (LTSSL) by leveraging parameter-efficient fine-tuning of pre-trained foundation models. The core idea is to enhance confidence calibration and generate more reliable pseudo-labels, which are crucial for addressing the imbalance inherent in long-tailed datasets. Furthermore, the paper extends this approach to open-world scenarios with LoFT-OW, specifically incorporating mechanisms to

en

Infini-gram: Scaling Unbounded N-gram Language Models

AI Post Transformers ·

2025/09/17

This April 2025 paper introduces Infini-gram, a novel engine designed to scale n-gram language models to an unprecedented 5 trillion tokens and support unbounded n (∞-gram LMs). Unlike traditional methods that rely on pre-computed count tables, Infini-gram leverages suffix arrays for efficient, low-latency calculation of n-gram and ∞-gram probabilities, even for extremely long contexts. The authors demonstrate that this modernized approach significantly improves the perplexity of neural Large

en

WebSailor-V2: Bridging Proprietary Agents with...

AI Post Transformers ·

2025/09/17

This September 2025 paper introduces WebSailor-V2, an open-source deep research agent developed by Alibaba Group's Tongyi Lab. The paper details a post-training pipeline that uses a novel synthetic data construction scheme, SailorFog-QA-V2, and a dual-environment reinforcement learning framework. WebSailor-V2, built on the Qwen3-30B-A3B model, demonstrates state-of-the-art performance among open-source agents and is competitive with leading proprietary systems on various web-agent benchmarks,

en

QuantAgent: Multi-Agent LLM for High-Frequency Trading

AI Post Transformers ·

2025/09/17

This September 2025 paper describes QuantAgent, a novel multi-agent large language model (LLM) framework designed for high-frequency quantitative trading based solely on price-derived market signals. The system decomposes trading decisions into four specialized agents—IndicatorAgent, PatternAgent, TrendAgent, and DecisionAgent—which analyze market dynamics from complementary perspectives and communicate through structured prompts. QuantAgent consistently outperforms baseline models across diverse

en

00:17:00

Generalist Reward Modeling with Inference-Time Scaling

AI Post Transformers ·

2025/09/16

This April 2025 paper introduces Self-Principled Critique Tuning (SPCT), a novel method designed to enhance the inference-time scalability of Generative Reward Models (GRMs) for various domains. It details how SPCT, through a combination of rejective fine-tuning and rule-based online reinforcement learning, facilitates the adaptive generation of principles and critiques, thereby improving the quality and inference-time scalability of GRMs. The paper compares different reward generation

en

1,015 results

Similar Podcasts

Lead With AI

Tamara Nall

Linux in the Ham Shack

Black Sparrow Media

Data Engineering Podcast

Tobias Macey

Eye On A.I.

Craig S. Smith

Reflections

Livewire Labs