· ai
[Paper] Decoupled Q-Chunking
Temporal-difference (TD) methods learn state and action values efficiently by bootstrapping from their own future value predictions, but such a self-bootstrappi...
-
- · ai
[Paper] CompanionCast: A Multi-Agent Conversational AI Framework with Spatial Audio for Social Co-Viewing Experiences
Social presence is central to the enjoyment of watching content together, yet modern media consumption is increasingly solitary. We investigate whether multi-ag...
- · ai
[Paper] Computational emotion analysis with multimodal LLMs: Current evidence on an emerging methodological opportunity
Emotions are central to politics and analyzing their role in political communication has a long tradition. As research increasingly leverages audio-visual mater...
- · ai
[Paper] Quantifying Emotional Tone in Tolkien's The Hobbit: Dialogue Sentiment Analysis with RegEx, NRC-VAD, and Python
This study analyzes the emotional tone of dialogue in J. R. R. Tolkien's The Hobbit (1937) using computational text analysis. Dialogue was extracted with regula...
- · ai
[Paper] Scaling Behavior of Discrete Diffusion Language Models
Modern LLM pre-training consumes vast amounts of compute and training data, making the scaling behavior, or scaling laws, of different models a key distinguishi...
- · ai
[Paper] Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants
Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scientific and engineerin...
- · ai
[Paper] Bayesian Symbolic Regression via Posterior Sampling
Symbolic regression is a powerful tool for discovering governing equations directly from data, but its sensitivity to noise hinders its broader application. Thi...
- · ai
[Paper] Learning Controllable and Diverse Player Behaviors in Multi-Agent Environments
This paper introduces a reinforcement learning framework that enables controllable and diverse player behaviors without relying on human gameplay data. Existing...
- · ai
[Paper] An Elementary Proof of the Near Optimality of LogSumExp Smoothing
We consider the design of smoothings of the (coordinate-wise) max function in mathbb{R}^d in the infinity norm. The LogSumExp function f(x)=ln(sum^d_iexp(x_i)) ...
- · ai
[Paper] LabelFusion: Learning to Fuse LLMs and Transformer Classifiers for Robust Text Classification
LabelFusion is a fusion ensemble for text classification that learns to combine a traditional transformer-based classifier (e.g., RoBERTa) with one or more Larg...
- · ai
[Paper] The FACTS Leaderboard: A Comprehensive Benchmark for Large Language Model Factuality
We introduce The FACTS Leaderboard, an online leaderboard suite and associated set of benchmarks that comprehensively evaluates the ability of language models t...
- · ai
[Paper] Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly
Retrieval-Augmented Generation (RAG) systems often fail on multi-hop queries when the initial retrieval misses a bridge fact. Prior corrective approaches, such ...