· ai
[Paper] LongVideoAgent: Multi-Agent Reasoning with Long Videos
Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods...
-
- · ai
[Paper] FedPOD: the deployable units of training for federated learning
This paper proposes FedPOD (Proportionally Orchestrated Derivative) for optimizing learning efficiency and communication cost in federated learning among multip...
- · ai
[Paper] Saddle-to-Saddle Dynamics Explains A Simplicity Bias Across Neural Network Architectures
Neural networks trained with gradient descent often learn solutions of increasing complexity over time, a phenomenon known as simplicity bias. Despite being wid...
- · ai
[Paper] Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many...
- · ai
[Paper] Cube Bench: A Benchmark for Spatial Visual Reasoning in MLLMs
We introduce Cube Bench, a Rubik's-cube benchmark for evaluating spatial and sequential reasoning in multimodal large language models (MLLMs). The benchmark dec...
- · ai
[Paper] Leveraging High-Fidelity Digital Models and Reinforcement Learning for Mission Engineering: A Case Study of Aerial Firefighting Under Perfect Information
As systems engineering (SE) objectives evolve from design and operation of monolithic systems to complex System of Systems (SoS), the discipline of Mission Engi...
- · ai
[Paper] Automated stereotactic radiosurgery planning using a human-in-the-loop reasoning large language model agent
Stereotactic radiosurgery (SRS) demands precise dose shaping around critical structures, yet black-box AI systems have limited clinical adoption due to opacity ...
- · ai
[Paper] Relu and softplus neural nets as zero-sum turn-based games
We show that the output of a ReLU neural network can be interpreted as the value of a zero-sum, turn-based, stopping game, which we call the ReLU net game. The ...
- · ai
[Paper] Improving ML Training Data with Gold-Standard Quality Metrics
Hand-tagged training data is essential to many machine learning tasks. However, training data quality control has received little attention in the literature, d...
- · ai
[Paper] Performative Policy Gradient: Optimality in Performative Reinforcement Learning
Post-deployment machine learning algorithms often influence the environments they act in, and thus shift the underlying dynamics that the standard reinforcement...
- · ai
[Paper] Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs
Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality tradeoff. W...
- · ai
[Paper] Distilling to Hybrid Attention Models via KL-Guided Layer Selection
Distilling pretrained softmax attention Transformers into more efficient hybrid architectures that interleave softmax and linear attention layers is a promising...