Research Brief
Key Takeaways
- • Key findings from research papers
Sources
- Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control
- RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems
- Critique of Agent Model
- Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation
- Can Language Model Agents be Helpful Circuit Explainers in Mechanistic Interpretability?
- Ensemble Feature Selection and Harris Hawks Optimization for Explainable Mental Health Risk Prediction in Female Sex Workers
- T2D-Bench: Evidence-Gated Evaluation of LLM Outputs for Type 2 Diabetes Using a Multi-Layer Clinical-Lifestyle Knowledge Graph
- OmniPath: A Multi-Modal Agentic Framework for Auditing Wheelchair Accessibility
- Navigating User Behavior toward Personalized Multimodal Generation
- Data Scale, Not Latency, Shapes Cross-Lingual Encoder Transfer in Streaming ASR
- Probing the Misaligned Thinking Process of Language Models
- FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning
- Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach
- SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis
- MVG-KAN: Multi-View Geo-Wind Guided KAN for PM$_{2.5}$ Forecasting
- Accelerating Disaggregated RL for Visual Generative LLMs with Diffusion-Based Parallelism and Trainer-Assisted Generation
- Prob-BBDM: a Probabilistic Brownian Bridge Diffusion Model for MRI sequence image-to-image translation
- Can Aggregate Invariants Accelerate Continuous Subgraph Matching? Limits, Laws, and a Dynamic Spectral Index
- ATRIA: Adaptive Traceable ECG Reporting with Iterative Agents
- Age of LLM: A Strategic 1v1 Benchmark for Reasoning, Diplomacy and Reliability of Large Language Models under Fog of War
- PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models
- Exploring the relationship between human-centric AI and firm idiosyncratic risks
- ReMMD: Realistic Multilingual Multi-Image Agentic Verification for Multimodal Misinformation Detection
- LemonHarness Technical Report
- Tractable Reasoning and Conjunctive Query Answering for Defeasible DL-Lite under Rational Closure
- Exploring Academic Influence of Algorithms by Co-occurrence Network Based on Full-text of Academic Papers
- The Geometry Behind Diffusion and Flow Matching: Gradient Flows and Geodesics in Wasserstein Space
- LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
- When CQs Go Wrong: Challenges in CQ Verification with OE-Assist
- Decentralised AI Training and Inference with BlockTrain
- CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning
- AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability
- Abstractions of Queries in Ontology-Based Data Access
- CompressKV: Semantic-Retrieval-Guided KV-Cache Compression for Resource-Efficient Long-Context LLM Inference
- On the Smallness of the Large Language Models Scaling Exponents
- The Latent Bridge: A Continuous Slow-Fast Channel for Real-Time Game Agents
- A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial
- Quant Convergence: Bridging Classical Value Investing and Modern Factor Models for Systematic Equity Selection
- Governed Shared Memory for Multi-Agent LLM Systems
- GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents
- Uncertainty-Aware Longitudinal Forecasting of Alzheimer's Disease Progression Using Deep Learning
- ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning
- ScaleToT: Generalizing Structured LLM Reasoning for Billion-Scale Low-Activity User Modeling
- Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for Encoder-Decoder Pre-trained Language Models
- Themis: An explainable AI-enabled framework for Reinforcement Learning with Human Feedback
- SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation
- Cost-Optimal Decision Diagrams for Stochastic Boolean Function Evaluation
- LaGO: Latent Action Guidance for Online Reinforcement Learning
- Scaling Laws for Task-Specific LLM Distillation
- Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment
- Difference-Making without Making a Difference
- Solving Inverse Problems of Chaotic Systems with Bidirectional Conditional Flow Matching
- Assessing Distribution Shift in Human Activity Recognition for Domain Generalization
- OpenThoughts-Agent: Data Recipes for Agentic Models
- World Models in Pieces: Structural Certification for General Agents
- Reinforcement Learning Towards Broadly and Persistently Beneficial Models
- Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for Driving VLAs
- Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning
- Grading the Grader: Lessons from Evaluating an Agentic Data Analysis System
- BluTrain: A C++/CUDA Framework for AI Systems
- Can Scale Save Us From Plasticity Loss in Large Language Models?
- AI Tokenomics: The Economics of Tokens, Computation, and Pricing in Foundation Models
- Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation
- ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling
- When Helpfulness Overrides Causal Caution: Context-Dependent Suppression and Recovery in LLMs
- An Introduction to Causal Reinforcement Learning
- VeryTrace: Verifying Reasoning Traces through Compilable Formalism and Structured Verification
- Bayesian control for coding agents
- Agentic AI for Bilevel Long-Term Optimization of Policy-Driven Physical Layer Systems
- Cycle-Consistent Neural Explanation of Formal Verification Certificates
Comments
Please log in to post a comment.