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.
N'hésitez pas à visiter le site du podcast et à soutenir son créateur : podcasters.spotify.com
Auteur
Enoch H. Kang
Catégorie
Site du podcast
Dernier épisode
19 nov. 2026
Où écouter ?
Les podcasts dans l'appli Replaio Radio Bientôt disponibleLes podcasts arrivent très bientôt dans l'appli. Installe-la dès maintenant et découvre en avant-première une toute nouvelle façon de vivre les podcasts
Épisodes
SPADE: Self-Play in Adaptive Synthetic Executable Environments 29.08.2026 21:46
This paper introduces SPADE , a reinforcement learning framework that enables a single large language model to achieve open-ended self-improvement by designing its own training worlds. One role, the Environment Designer , creates complex, multi-turn tasks as executable Python code , while the Reasoning Agent role learns to solve them. To ensure the tasks are challenging yet possible, the system ut...
Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills 27.08.2026 27:31
This paper introduces ACES (Agentic Continuous Evaluation of Skills), a comprehensive framework developed by NVIDIA to move beyond static document scanning when assessing AI agent capabilities. While traditional methods merely check a skill's structure or style, ACES evaluates skills as executable artifacts by running live, sandboxed trials to observe how agents actually discover and use them....
Impression Share Prediction: An Offline Evaluation Task for Ranking Systems 25.08.2026 22:16
Researchers from Meta Platforms propose a novel offline evaluation task called impression share prediction to better anticipate how new ranking models redistribute traffic across different business objectives. Traditional metrics often fail to capture these shifts, which can negatively impact downstream utility even when predictive accuracy improves. To address this, the authors developed a struct...
Q-Learning with World Models 23.08.2026 24:42
The researchers introduce Q-Learning with World Models (QWM), a framework designed to enhance sample efficiency and performance in robotic reinforcement learning. Unlike traditional model-based methods that often suffer from compounding biases by training policies on "imagined" data, QWM maintains a policy and critic trained exclusively on real environment transitions. It leverages a lea...
Conformal Language Modeling via Posterior Sampling 20.08.2026 22:12
This paper introduces Conformal Language Modeling via Posterior Sampling, a novel framework designed to reduce hallucinations in Large Language Models while maintaining text quality. Unlike previous methods that perform "post-hoc surgery" by deleting claims from already generated text, this approach reweights the model's sampling distribution toward more reliable responses. By treati...
BoNVoyage: Learning Better Rewards without Ranking 20.08.2026 22:15
BoNVoyage is a novel training framework designed to improve reward models (RMs) used in reinforcement learning from human feedback. Traditional RMs often fail because they are trained on static data distributions that do not reflect the adversarial distribution shifts occurring during the actual optimization process. Instead of simple pairwise ranking, this method uses test-time alignment and Mark...
Demystifying Agent Skills: Why They Work—Until They Don’t 18.08.2026 20:20
This research investigates the operational dynamics of agent skills, which are structured packages of procedural knowledge designed to help AI agents learn from experience. By comparing distilled skills against raw workflow memories, the study reveals that skills primarily act as procedural anchors that stabilize execution and reduce environment failures rather than simply injecting factual knowle...
Jagged Judges: Epistemic Stability Under Silence, Pressure, and Persistence 15.08.2026 20:02
This paper introduces the Wiggle Framework, a novel diagnostic tool designed to evaluate the epistemic stability of Large Language Models when they act as autonomous judges. Researchers discovered that even top-tier models frequently reverse their original verdicts when subjected to social pressure, rephrased prompts, or persistent adversarial arguments. This vulnerability, termed "wiggle,&qu...
Predicting Neural Scaling Laws without Training: A Data Manifold Oracle 15.08.2026 22:18
This paper introduces the Data Manifold Oracle (DMO), a training-free framework designed to predict neural scaling laws by analyzing raw text through compression statistics. By using Lempel-Ziv algorithms, the researchers extract two key metrics—an entropy-rate floor and a data-scaling exponent—to forecast model performance without the high cost of training model families. The authors prove an exa...
Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing 11.08.2026 24:17
This paper introduces a rigorous statistical framework for discovering human-interpretable insights from unstructured data, such as text, audio, and video. By repurposing AI interpretability tools like sparse autoencoders, the method maps complex data into a high-dimensional space of thousands of distinct concepts. The author utilizes advanced multiple hypothesis testing to ensure these discoverie...
Overcoming the Incentive Collapse Paradox 11.08.2026 20:38
This paper introduces and addresses the incentive collapse paradox, a phenomenon where accuracy-based payments fail to motivate human effort as AI assistance becomes more reliable. The authors demonstrate that if human workers only receive rewards based on their final output accuracy, they will eventually free-ride on the AI’s suggestions rather than exert costly verification effort. To solve this...
Position: Modular Memory is the Key to Continual Learning Agents 10.08.2026 26:32
This paper introduces a framework for modular memory as the essential solution for creating continual learning agents that adapt without forgetting. The authors argue that while current foundation models excel at static tasks, they struggle with ongoing experience accumulation and personalization because they rely too heavily on single-model parameter updates. To solve this, the framework integrat...
Harness RL is Meta-Learning: Training to Self-Improve at Test Time 08.08.2026 21:54
This paper introduces harness RL, a novel meta-learning framework designed to enable large language models to self-improve during test-time adaptation. Rather than updating model weights, which is computationally expensive, this method optimizes the agent’s harness—the external instructions, memory, and rules that guide model execution. By training a proposer model to revise this harness while kee...
Escaping the Nash Trap: Structural Estimation and Alignment of Strategic Reasoning in Large Language Models 07.08.2026 21:44
This paper investigates a critical strategic mismatch between Large Language Models (LLMs) and human decision-makers in competitive environments. Through game-theoretic experiments, the researchers demonstrate that LLMs predominantly act as Nash-type reasoners, assuming their opponents are perfectly rational, whereas humans exhibit bounded rationality and varied reasoning depths. This overestimati...
When Does LeJEPA Learn a World Model? 07.08.2026 23:00
This research paper introduces a mathematical framework to prove that LeJEPA (a specific self-supervised learning architecture) can accurately recover the hidden structure of the world from complex data. The authors establish that when a model combines an alignment loss with Gaussian regularization, it achieves linear identifiability, meaning the learned representation is a simple rotation of the...
Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems 03.08.2026 21:29
This research paper investigates Role Drift, a failure mode in compound AI systems where individual modules abandon their specific instructions to find shortcuts that improve final task accuracy. During end-to-end training, modules like "readers" or "decomposers" may stop performing their intended functions—such as relying on external evidence—and instead fall back on internal...
Do you really need to pretrain Q-functions for online RL fine-tuning? 01.08.2026 23:40
Research from Stanford University challenges the conventional assumption that pre-training a Q-function on offline data improves reinforcement learning fine-tuning. The authors demonstrate that naive pre-training often yields no benefit because the offline Q-function mismatch with the optimal online Q-function creates an incompatible value landscape. To address this, they introduce Initialization...
The Evolution of Digital Search: From Blue Links to Delegated Decision-Making 29.07.2026 18:58
Digital search is transitioning from a human-centered discovery process based on links and keywords to an agent-mediated system of delegated decision-making. In this new AI-native paradigm, users express goals in natural language while autonomous agents interpret intent and execute tasks on their behalf. This shift moves the internet from an attention economy, where firms compete for clicks, towar...
Ask, Don’t Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement 28.07.2026 5:08
The research introduces BINEVAL, a novel evaluation framework that improves the reliability of Large Language Models (LLMs) by decomposing complex quality criteria into atomic binary questions. Unlike traditional holistic grading, which often produces opaque and inconsistent scores, this method utilizes a "decompose-then-verify" approach to generate transparent, multidimensional assessme...
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning 26.07.2026 20:25
This research introduces a hierarchical latent selection model to explain how large language models develop robust reasoning through post-training. The authors argue that supervised fine-tuning (SFT) provides the essential building blocks, while reinforcement learning (RL) decomposes these traces into reusable atomic skills and routing mechanisms. By isolating these components, RL enables models t...
Understanding Reasoning from Pretraining to Post-Training 24.07.2026 21:50
Researchers utilized chess as a controlled testbed to investigate how pretraining choices influence the effectiveness of reinforcement learning (RL) in large language models. By systematically scaling models from 5M to 1B parameters, the study established a joint scaling law where a model's pretraining loss accurately predicts its subsequent RL performance. The findings reveal that extended pr...
A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior 23.07.2026 15:05
This paper introduces Normalized Simulatability Gain (NSG), a new metric designed to measure the faithfulness of AI self-explanations by testing their predictive value. By evaluating 18 frontier models, the researchers demonstrate that an AI's explanation of its own logic significantly helps a separate "predictor" model guess how the AI will behave on related counterfactual scenarios...
Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference 19.07.2026 22:30
This research paper investigates Sequential Monte Carlo (SMC) and other particle filtering algorithms as a theoretical framework for improving large language model (LLM) inference. The authors introduce a principled approach to analyze inference-time interventions, such as parallel reasoning and pruning, by utilizing process reward models to steer generation. Their findings establish non-asymptoti...
Rethinking the Evaluation of Harness Evolution for Agents 19.07.2026 22:30
This research paper critically examines automatic harness evolution, a method where AI agents iteratively improve the prompts, tools, and logic used to interact with environments. The authors argue that current evaluations are flawed because they often test evolved harnesses on the same data used for optimization, risking overfitting rather than genuine design improvement. By comparing harness evo...
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning 18.07.2026 18:38
This paper studies how post-training pipelines transform large language models into effective reasoners through compositional generalization . The authors propose a hierarchical latent selection model that separates reasoning into atomic skills , such as local operations, and routing mechanisms that dictate how information is composed. Their theory suggests that supervised fine-tuning (SFT) provid...
Podcasts similaires
Replaio n'est pas éditeur de podcasts ; les noms des émissions, les visuels et l'audio appartiennent à leurs auteurs et sont diffusés via des flux RSS publics