Enoch H. Kang

Best AI papers explained

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

Vizitează neapărat site-ul podcastului și susține-i creatorul: podcasters.spotify.com

Autor

Enoch H. Kang

Categorie

Technology

Site-ul podcastului

podcasters.spotify.com

Cel mai nou episod

19 nov. 2026

Unde asculți?

Podcasturi în aplicație Replaio Radio În curând

Podcasturile ajung în curând în aplicație. Instaleaz-o acum și fii primul care descoperă o abordare complet nouă a podcasturilor

Descarcă din Google Play Instalează gratuit Android 10 mil.+ descărcări · nota 4,7+ iOS în curând

Episoade

Black-Box On-Policy Distillation of Large Language Models 20.11.2025

This paper introduces a novel technique called **Generative Adversarial Distillation (GAD)** for knowledge transfer from a large, proprietary teacher language model (LLM), such as GPT-5-Chat, to a smaller student LLM in a **black-box setting**. Black-box distillation is necessary when the student only has access to the teacher’s final text outputs, not its internal parameters or probabilities. GAD...

Solving a million step LLM task with zero errors 20.11.2025

This research paper introduces how we can reliably complete complex, multi-step tasks with zero errors. The core concept is **extreme decomposition** of a task into minimal subtasks handled by focused "microagents," which overcomes the inherent, escalating error rate of monolithic LLMs over long horizons. This modular approach integrates an **efficient error correction** mechanism—specifically, a...

Not All Thoughts Matter: Selective Attention for Efficient Reasoning 19.11.2025

This paper studies an inference-time optimization technique designed to reduce the high computational cost of reasoning-optimized large language models (LLMs), which generate long chains of thought. LLMs' self-attention mechanism typically scales quadratically with sequence length, making long reasoning chains prohibitively expensive. RWR addresses this by exploiting the redundancy in intermed...

Sample-Efficient Parametric Learning from Natural Language 19.11.2025

This research paper provides a novel approach for sample-efficient parametric learning in large language models (LLMs) using natural language feedback, addressing the transience of traditional in-context learning (ICL) and the data inefficiency of standard fine-tuning. The authors propose a simple three-step method: obtaining natural language feedback, sampling a generation conditioned on that fee...

Bayesian Optimization in Language space: An Eval-Efficient AI Self-Improvement Framework 18.11.2025

This paper discusses how to design an evaluation-efficient self-improving AI systems that beats GEPA for societal and business problems like ad optimization where the cost of generating new content is low but evaluation is expensive. It argues that traditional human-driven optimization is slow and bottlenecked by content generation, but generative AI has shifted the bottleneck to efficient evaluat...

Context Engineering: Sessions, Memory 16.11.2025

This whitepaper by Google titled **"Context Engineering: Sessions & Memory,"** authored by Kimberly Milam and Antonio Gulli in November 2025, which provides a detailed guide to building stateful, intelligent Large Language Model (LLM) agents. The document defines **Context Engineering** as the process of dynamically managing information within an LLM's context window, emphasizing two core, interco...

The Era of Agentic Organization: Learning to Organize with Language Models 15.11.2025

This paper introduces **Asynchronous Thinking (AsyncThink)**, a novel paradigm for large language model (LLM) reasoning designed to enable **agentic organization** and collaborative problem-solving. AsyncThink employs an **organizer-worker thinking protocol** where an LLM acts as an organizer that dynamically structures concurrent processes using **Fork and Join actions**, while workers execute su...

Understanding neural networks through sparse circuits 14.11.2025

This paper by OpenAI discusses a new approach to **neural network interpretability** through the use of **sparse circuits**. The authors explain that understanding the behavior of complex, hard-to-decipher neural networks is critical for safety and oversight as AI systems become more capable. They distinguish their work on **mechanistic interpretability**, which seeks to fully reverse-engineer com...

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning 14.11.2025

The academic paper introduces Supervised Reinforcement Learning (SRL), a novel training framework for Large Language Models (LLMs) developed by researchers from Google Cloud AI Research and UCLA to address the difficulty of multi-step reasoning. SRL reformulates problem-solving as a sequence of logical actions, providing dense, step-wise rewards based on the similarity between the model's gene...

Multi-Agent Evolve: LLM Self-Improvement Through Co-Evolution 14.11.2025

This research paper introduces Multi-Agent Evolve (MAE), a novel reinforcement learning framework designed to enable large language models (LLMs) to self-improve their general reasoning abilities without relying on human-curated datasets or verifiable external rewards. MAE accomplishes this through a system where a single LLM is instantiated into three interacting roles—a Proposer that creates cha...

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics 14.11.2025

This paper introduces a novel self-supervised learning framework designed to resolve the pervasive issue of representation collapse in existing Joint-Embedding Predictive Architectures (JEPAs). It establishes a theoretical foundation by proving that an isotropic Gaussian distribution is the optimal embedding distribution for minimizing the worst-case risk across various downstream tasks. To enforc...

PREFDISCO: Evaluating Proactive Personalization through Interactive Preference Discovery 12.11.2025

This paper introduce a new meta-benchmark designed to evaluate large language models' (LLMs) ability to perform **interactive preference discovery** and response personalization through conversation. The framework converts existing benchmarks into interactive tasks by assigning **psychologically-grounded personas** with hidden preferences to be discovered by the AI. Evaluation of numerous frontier...

Reusing pre-training data at test time is a compute multiplier 10.11.2025

The academic paper investigates the efficiency of Large Language Model (LLM) pre-training by quantifying the amount of knowledge left unextracted from training datasets. The authors demonstrate that employing retrieval-augmented generation (RAG) at test time, which involves reusing the pre-training data, leads to significant accuracy improvements across benchmarks like MMLU, Math-500, and SimpleQA...

Scaling Agent Learning via Experience Synthesis 09.11.2025

The academic paper proposes **DreamGym**, a novel, unified framework for scaling agent learning using reinforcement learning (RL) by synthesizing diverse experiences instead of relying on costly real-environment rollouts. The core of this system is a **reasoning-based experience model** that abstracts environment dynamics into a textual space, enabling the generation of consistent state transition...

Continuous Autoregressive Language Models 08.11.2025

This paper introduces **Continuous Autoregressive Language Models (CALM)**, a new paradigm designed to overcome the efficiency limitations of conventional, token-by-token generation in Large Language Models (LLMs). CALM achieves significant computational savings by employing a robust **autoencoder** to compress a chunk of $K$ discrete tokens into a single, high-fidelity continuous vector, thereby...

Toward a Theory of Agents as Tool-Use Decision-Makers 07.11.2025

This position paper argues for a new epistemic theory of agents that views internal reasoning and external actions as equivalent epistemic tools for acquiring knowledge. The core argument is that for an agent to achieve optimal and efficient behavior, its tool use decision boundary must be aligned with its knowledge boundary, meaning it should only resort to external tools when necessary knowledge...

Nested Learning: The Illusion of Deep Learning Architectures 05.11.2025

This paper introduces Nested Learning (NL), a new paradigm that addresses fundamental challenges in AI self-improvement, continual learning and memory for models like Large Language Models (LLMs). NL suggests that existing deep learning methods compress their "context flow" and explains how in-context learning emerges in large models. The authors propose the HOPE architecture, a self-ref...

GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding 05.11.2025

This paper introduce the GST-UNet (G-computation Spatio-Temporal UNet), a novel neural framework designed for causal inference using spatiotemporal observational data, particularly when analyzing a single observed trajectory. This framework integrates a U-Net encoder with ConvLSTM and attention mechanisms to learn spatiotemporal dependencies and explicitly address challenges like interference, spa...

Beyond a million tokens: benchmarking and enhancing long-term memory in llms 04.11.2025

This paper introduces a research paper focused on improving **Large Language Model (LLM) performance on tasks requiring long-term conversational memory**. The authors address limitations in existing evaluation methods by presenting a new framework that automatically generates **long, coherent conversations up to 10 million tokens** and **BEAM**, a benchmark dataset with 100 dialogues and 2,000 pro...

Agentic Economic Modeling 03.11.2025

This paper introduces Agentic Economic Modeling (AEM), a rigorous framework proposed by superstar social scientists that leverages Large Language Models (LLMs) to reliably simulate economic decisions and generate counterfactual data for econometric inference. The core innovation is a three-stage pipeline—Generation, Correction, and Inference—designed to overcome the systematic biases found in raw...

Emergent Introspective Awareness in Large Language Models 03.11.2025

This research by anthropic investigates the existence of **functional introspective awareness** in large language models (LLMs), specifically focusing on Anthropic's Claude models. The core methodology involves using **concept injection**, where researchers manipulate a model's internal activations with representations of specific concepts to see if the model can accurately **report on these alter...

Can Large reasoning models self-train? 01.11.2025

This paper investigates whether large reasoning models can sustain self-training using Reinforcement Learning (RL), specifically employing majority voting as a self-feedback mechanism, termed Self-Rewarded Training (SRT). The research demonstrates that this basic approach initially improves the model's reasoning performance and enhances the quality of its self-generated feedback, achieving per...

ALITA-G: Self-Evolving Generative Agent for Agent Generation 01.11.2025

This paper proposes a method for transforming a general-purpose large language model agent into a domain-specific expert. This system achieves specialization by systematically generating, abstracting, and curating reusable Model Context Protocol (MCP) tools from successful task executions, which are then stored in an MCP Box. At inference time, a Retrieval-Augmented Generation (RAG) mechanism sele...

Self-improving LLM agents at test-time 30.10.2025

The academic paper proposes a novel framework called Test-Time Self-Improvement (TT-SI) for training Large Language Model (LLM) agents more efficiently by adapting them on-the-fly during inference. This new paradigm is motivated by the high cost and inefficiency of traditional large-scale fine-tuning, which often involves redundant data. TT-SI operates in three steps: Self-Awareness identifies unc...

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization 30.10.2025

This paper recasts the complex offline RL problem as standard supervised fine-tuning (SFT) techniques that directly optimizes for rewards. Authors show that their method empirically outperforms state-of-the-art baselines such as SFT and Direct Preference Optimization (DPO) across various QA benchmarks. The experiments focus on fixed-horizon conversational policies where the agent either reasons ab...

Ascultă podcastul Best AI papers explained în Replaio

Radio și podcasturi într-o singură aplicație - gratuit și fără înregistrare. Instaleaz-o azi și nu rata lansarea

Descarcă din Google Play

Replaio nu este editorul podcasturilor; numele emisiunilor, coperțile și materialul audio aparțin autorilor lor și sunt distribuite prin fluxuri RSS publice