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.

Be sure to visit the podcast's website and support the creator: podcasters.spotify.com

Author

Enoch H. Kang

Category

Technology

Podcast website

podcasters.spotify.com

Latest episode

Nov 19, 2026

Where to listen?

Podcasts in the app Replaio Radio Coming soon

Podcasts are coming to the app soon. Install now and be the first to see a whole new take on podcasts

Get it on Google Play Install for free Android 10M+ downloads · 4.7+ rating iOS soon

Episodes

Diffusion Guidance Is a Controllable Policy Improvement Operator 02.06.2025

This document introduces  CFGRL , a novel framework that bridges generative modeling, specifically diffusion guidance, and reinforcement learning. The core idea is to treat policy improvement as guiding a diffusion model, allowing for  simple training  akin to supervised learning while still enabling  performance beyond the initial dataset . CFGRL can improve policies by combining a reference poli...

Alita: Generalist Agent With Self-Evolution 02.06.2025

This academic paper presents Alita , a novel generalist agent designed to enhance scalable agentic reasoning with a focus on minimal predefinition and maximal self-evolution . Unlike conventional agents that rely heavily on pre-designed tools and workflows, Alita utilizes a radically simple design with a core web agent and the ability to autonomously generate, refine, and reuse capabilities via Mo...

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning 02.06.2025

This academic paper proposes a local data attribution framework for online reinforcement learning (RL) . The framework uses influence functions to identify which training data records negatively impact the RL agent's learning within each training round. By filtering out these harmful records , the proposed method, called Influence-guided Intervention and Filtering (IIF) , demonstrates improved...

Learning Compositional Functions with Transformers from Easy-to-Hard Data 02.06.2025

This paper presents a theoretical analysis of how transformers can learn k-fold composition tasks , which involve combining multiple permutations. It proposes that transformers can achieve this through a hierarchical process , where each layer learns progressively more complex compositions, referred to as " hops ." The document details a curriculum learning strategy (Algorithm 1) and a m...

Preference Learning with Response Time 02.06.2025

This academic paper introduces a new approach to preference learning by  incorporating response time data  alongside traditional binary choices. The authors highlight that while standard preference learning relies solely on which option a user prefers, the  speed of the decision can provide valuable information  about the strength of that preference. They propose novel methodologies, including a ...

Accelerating RL for LLM Reasoning with Optimal Advantage Regression 31.05.2025

This research introduces A-PO *, a new reinforcement learning approach for refining large language models to enhance their reasoning capabilities. Unlike existing methods that are often computationally expensive and memory-intensive due to requiring multiple generations per prompt or explicit critic networks, A*-PO streamlines the process. It accomplishes this by initially estimating the optimal v...

Algorithms for reliable decision-making need causal reasoning 31.05.2025

The paper emphasizes the necessity of causal reasoning for reliable algorithmic decision-making (ADM). It explains that real-world decisions involve cause-and-effect relationships , making causal challenges inherent in ADM systems. To ensure reliability, ADM algorithms must incorporate explicit assumptions about the underlying causal structure . The text highlights the distinction between causal e...

Belief Attribution as Mental Explanation: The Role of Accuracy, Informativity, and Causality 31.05.2025

This academic paper explores how people attribute beliefs to others as a way of explaining their actions, focusing on the explanatory strength of a belief rather than just its probability. The authors developed a computational model that assesses this strength using three factors: accuracy, informativity, and causal relevance . Through an experiment where participants ranked belief statements desc...

Distances for Markov chains from sample streams 31.05.2025

This document presents a novel approach for estimating the similarity between Markov chains using only sampled data, without requiring full knowledge of their transition probabilities. The authors leverage the recent finding that bisimulation metrics , a tool for quantifying stochastic process similarity, are equivalent to optimal transport distances . They reformulate the problem as a linear prog...

When and Why LLMs Fail to Reason Globally 31.05.2025

This research explores why Large Language Models (LLMs) struggle with tasks requiring global reasoning over long inputs. The authors propose that these limitations stem from constraints on information flow within LLMs, formalizing this with the Bounded Attention Prefix Oracle (BAPO) model. They classify problems as BAPO-easy or BAPO-hard , predicting that LLMs will fail on the latter. Empirical re...

IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis 31.05.2025

This paper describes IDA-Bench , a new benchmark for evaluating Large Language Models (LLMs) as interactive data analysis agents . Unlike existing benchmarks that focus on single-turn interactions, IDA-Bench assesses LLMs in multi-round dialogues with a simulated user, mirroring the iterative and subjective nature of real-world data analysis. Tasks are derived from complex Kaggle notebooks and pre...

No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference 31.05.2025

This paper examines the performance of Prediction-Powered Inference (PPI++) , a statistical method combining labeled and unlabeled data for estimation. While previous work suggested PPI++ always improved over using labeled data alone asymptotically, this analysis provides a finite-sample "no free lunch" result . It demonstrates that PPI++ only outperforms classical methods if the correla...

Accelerating RL for LLM Reasoning with Optimal Advantage Regression 31.05.2025

This research introduces A-PO *, a new reinforcement learning approach for refining large language models to enhance their reasoning capabilities. Unlike existing methods that are often computationally expensive and memory-intensive due to requiring multiple generations per prompt or explicit critic networks, A*-PO streamlines the process. It accomplishes this by initially estimating the optimal v...

Statistical Inference for Online Algorithms 31.05.2025

This paper proposes HulC , a statistically sound and computationally efficient method for constructing confidence regions from the output of online algorithms , such as Stochastic Gradient Descent (SGD) . Unlike traditional methods like the Wald interval , which require multiple passes over the data and can be computationally expensive, HulC provides rate-optimal and asymptotically valid confidenc...

Prismatic Synthesis for Diverse LLM Reasoning Data 31.05.2025

This paper investigates how data diversity impacts the generalization of large language models (LLMs) , particularly in reasoning tasks. The authors introduce G-Vendi, a novel metric that quantifies diversity based on the entropy of model-induced gradients , showing a strong correlation with out-of-distribution performance. Building on this, they propose Prismatic Synthesis, a framework for genera...

Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents 31.05.2025

This position paper argues for a reassessment of uncertainty quantification in large language model (LLM) agents . The authors contend that the traditional division between aleatoric (irreducible) and epistemic (reducible) uncertainty is insufficient for the interactive nature of LLM agents, especially given their propensity to produce incorrect outputs. They highlight how existing definitions of...

The Agentic Economy 30.05.2025

This paper from Microsoft Research discusses the potential for generative AI to transform the economy by enabling an agentic economy , where AI agents act on behalf of users and businesses to facilitate transactions. The authors argue that the most significant impact of AI will be in reducing communication frictions between consumers and businesses, which could lead to markets being reorganized an...

Statistics for Large Language Models 29.05.2025

This academic paper explores the critical role of statistical foundations in the development and application of Large Language Models (LLMs) . The author argues that LLMs are fundamentally statistical due to their reliance on vast datasets and their probabilistic generation processes . Their "black-box" nature , stemming from complexity and scale, further necessitates statistical methods...

Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search 29.05.2025

This academic paper presents Bayes-adaptive Monte-Carlo Planning (BAMCP) , a novel algorithm designed to tackle the computational challenges of Bayesian model-based reinforcement learning . The core idea is to use Monte-Carlo tree search within a modified framework that avoids the computationally expensive posterior belief updates at every step within the search tree. Instead, BAMCP employs root s...

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning 29.05.2025

This paper explores how to enhance Large Language Model (LLM) reasoning by moving beyond conventional reinforcement learning (RL) methods. Standard RL confines exploration to the training phase and relies solely on the current state, failing to fully utilize reflective reasoning at test time. The authors propose Bayes-Adaptive RL (BARL) , a framework that explicitly optimizes for test-time general...

Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL 29.05.2025

This paper introduces Planning with a Natural Language Critic (PNLC) , a novel approach for improving the planning capabilities of large language models (LLMs) in complex interactive tasks without relying on computationally expensive reinforcement learning (RL) fine-tuning or extensive inference-time search. PNLC trains a lightweight, goal-conditioned value function offline that predicts the likel...

Value-Guided Search for Efficient Chain-of-Thought Reasoning 29.05.2025

This paper introduces  Value-Guided Search (VGS) , a novel method for improving the reasoning capabilities and efficiency of large language models (LLMs) on complex tasks like competition math. Unlike prior methods that rely on fine-grained, step-by-step feedback, VGS uses a  token-level value model  trained on large datasets of reasoning traces. This model guides a  block-wise search  process, se...

Shallow Preference Signals: Large Language model aligns even better without truncated data? 29.05.2025

This academic paper investigates the phenomenon of shallow preference signals in large language models (LLMs), where the critical information for determining human preference in a response is often found in the early tokens. Experiments show that training reward models and Direct Preference Optimization (DPO) models on truncated preference datasets, using only the initial part of responses, can ac...

Gaming Tool Preferences in Agentic LLMs 29.05.2025

This academic paper explores a significant vulnerability in how large language models (LLMs) select and use external tools , which are crucial for their agentic capabilities. The research demonstrates that subtle modifications to a tool's natural language description , without altering its function, can dramatically influence whether an LLM chooses to use it, sometimes by a factor of over 10 t...

Partner Modelling Emerges in Recurrent Agents (But Only When It Matters) 29.05.2025

This paper explores whether artificial agents can develop an understanding of their partners' abilities during collaborative tasks without being explicitly programmed to do so. Researchers trained recurrent neural network (RNN) agents to play a cooperative game called "Overcooked-AI" with a variety of partners having different skill levels. The study found that these agents developed...

Listen to the Best AI papers explained podcast in Replaio

Radio and podcasts in one app - free, with no sign-up. Install today and do not miss the launch

Get it on Google Play

Replaio is not a podcast publisher; show names, artwork and audio belong to their authors and are distributed through public RSS feeds.