[2026-03-06] 📚 Updates in #LRM
(1) PrefDisco: Benchmarking Proactive Personalized Reasoning
(2) PrefDisco: Benchmarking Proactive Personalized Reasoning
🔍 More at researchtrend.ai/communities/LRM
[2026-03-06] 📚 Updates in #DiffM
(1) ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
(2) Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion
🔍 More at researchtrend.ai/communities/DiffM
[2026-03-06] 📚 Updates in #AI4CE
(1) ms-Mamba: Multi-scale Mamba for Time-Series Forecasting
(2) Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
(3) Flowers: A Warp Drive for Neural PDE Solvers
🔍 More at researchtrend.ai/communities/AI4CE
[2026-03-06] 📚 Updates in #VLM
(1) SAMPO-Path: Segmentation Intent-Aligned Preference Optimization for Pathology Foundation Model Segmentation
(2) Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented Design
🔍 More at researchtrend.ai/communities/VLM
[2026-03-06] 📚 Updates in #AI4TS
(1) ms-Mamba: Multi-scale Mamba for Time-Series Forecasting
(2) The Volterra signature
(3) The Volterra signature
(4) Visioning Human-Agentic AI Teaming: Continuity, Tension, and Future Research
🔍 More at researchtrend.ai/communities/AI4TS
[2026-03-06] 📚 Updates in #ELM
(1) Towards Trustworthy Legal AI through LLM Agents and Formal Reasoning
(2) Same Input, Different Scores: A Multi Model Study on the Inconsistency of LLM Judge
🔍 More at researchtrend.ai/communities/ELM
[2026-03-06] 📚 Updates in #OffRL
(1) VRM: Teaching Reward Models to Understand Authentic Human Preferences
(2) VRM: Teaching Reward Models to Understand Authentic Human Preferences
🔍 More at researchtrend.ai/communities/OffRL
[2026-03-06] 📚 Updates in #LLMAG
(1) INMS: Memory Sharing for Large Language Model based Agents
(2) A Signal Contract for Online Language Grounding and Discovery in Decision-Making
🔍 More at researchtrend.ai/communities/LLMAG
[2026-03-06] 📚 Updates in #AAML
(1) Secure human oversight of AI: Threat modeling in a socio-technical context
(2) Breaking and Fixing Defenses Against Control-Flow Hijacking in Multi-Agent Systems
🔍 More at researchtrend.ai/communities/AAML
[2026-03-06] 📚 Updates in #VGen
(1) EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation
(2) Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
🔍 More at researchtrend.ai/communities/VGen
[2026-03-06] 📚 Updates in #MedIm
(1) SAMPO-Path: Segmentation Intent-Aligned Preference Optimization for Pathology Foundation Model Segmentation
(2) Structure-Guided Histopathology Synthesis via Dual-LoRA Diffusion
🔍 More at researchtrend.ai/communities/MedIm
[2026-03-06] 📚 Updates in #MQ
(1) Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices
(2) Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices
🔍 More at researchtrend.ai/communities/MQ
[2026-03-06] 📚 Updates in #AuLLM
(1) Measuring the Redundancy of Decoder Layers in SpeechLLMs
(2) Measuring the Redundancy of Decoder Layers in SpeechLLMs
(3) WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation
🔍 More at researchtrend.ai/communities/AuLLM
[2026-03-06] 📚 Updates in #LM&Ro
(1) Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation
(2) Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation
🔍 More at researchtrend.ai/communities/LM&Ro
[2026-03-06] 📚 Updates in #ALM
(1) Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework
(2) Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework
🔍 More at researchtrend.ai/communities/ALM
[2026-03-06] 📚 Updates in #MoE
(1) NeuronMoE: Neuron-Guided Mixture-of-Experts for Efficient Multilingual LLM Extension
(2) NeuronMoE: Neuron-Guided Mixture-of-Experts for Efficient Multilingual LLM Extension
🔍 More at researchtrend.ai/communities/MoE
[2026-03-06] 📚 Updates in #CML
(1) cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context
(2) Learning Causal Structure of Time Series using Best Order Score Search
🔍 More at researchtrend.ai/communities/CML
[2026-03-06] 📚 Updates in #FedML
(1) Good-Enough LLM Obfuscation (GELO)
(2) Good-Enough LLM Obfuscation (GELO)
(3) FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning
🔍 More at researchtrend.ai/communities/FedML
[2026-03-06] 📚 Updates in #ReLM
(1) Enhancing Zero-shot Commonsense Reasoning by Integrating Visual Knowledge via Machine Imagination
(2) Enhancing Zero-shot Commonsense Reasoning by Integrating Visual Knowledge via Machine Imagination
🔍 More at researchtrend.ai/communities/ReLM
[2026-03-06] 📚 Updates in #CLL
(1) Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation
(2) Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation
(3) Replaying pre-training data improves fine-tuning
🔍 More at researchtrend.ai/communities/CLL
[2026-03-06] 📚 Updates in #3DGS
(1) Gaussian Wardrobe: Compositional 3D Gaussian Avatars for Free-Form Virtual Try-On
(2) DSA-SRGS: Super-Resolution Gaussian Splatting for Dynamic Sparse-View DSA Reconstruction
🔍 More at researchtrend.ai/communities/3DGS
[2026-03-06] 📚 Updates in #Mamba
(1) ms-Mamba: Multi-scale Mamba for Time-Series Forecasting
(2) MambaTAD: When State-Space Models Meet Long-Range Temporal Action Detection
(3) Mask-aware inference with State-Space Models
🔍 More at researchtrend.ai/communities/Mamba
[2026-03-06] 📚 Updates in #LM&MA
(1) AbAffinity: A Large Language Model for Predicting Antibody Binding Affinity against SARS-CoV-2
(2) AbAffinity: A Large Language Model for Predicting Antibody Binding Affinity against SARS-CoV-2
🔍 More at researchtrend.ai/communities/LM&MA
[2026-03-06] 📚 Updates in #AILaw
(1) Towards Trustworthy Legal AI through LLM Agents and Formal Reasoning
(2) Guidelines for the Annotation and Visualization of Legal Argumentation Structures in Chinese Judicial Decisions
🔍 More at researchtrend.ai/communities/AILaw
[2026-03-06] 📚 Updates in #MoMe
(1) Federated Heterogeneous Language Model Optimization for Hybrid Automatic Speech Recognition
(2) Federated Heterogeneous Language Model Optimization for Hybrid Automatic Speech Recognition
🔍 More at researchtrend.ai/communities/MoMe
[2026-03-06] 📚 Updates in #RALM
(1) CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models
(2) CTRL-RAG: Contrastive Likelihood Reward Based Reinforcement Learning for Context-Faithful RAG Models
🔍 More at researchtrend.ai/communities/RALM
[2026-03-06] 📚 Updates in #MLLM
(1) Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild
(2) Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild
🔍 More at researchtrend.ai/communities/MLLM
[2026-03-06] 📚 Updates in #LLMSV
(1) Why Is RLHF Alignment Shallow? A Gradient Analysis
(2) Why Is RLHF Alignment Shallow? A Gradient Analysis
(3) Latent Policy Steering through One-Step Flow Policies
🔍 More at researchtrend.ai/communities/LLMSV
[2026-03-06] 📚 Updates in #FAtt
(1) cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context
(2) Fusion-CAM: Integrating Gradient and Region-Based Class Activation Maps for Robust Visual Explanations
🔍 More at researchtrend.ai/communities/FAtt
[2026-03-06] 📚 Updates in #HILM
(1) Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval
(2) Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
(3) Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
🔍 More at researchtrend.ai/communities/HILM
