[2026-03-13] 📚 Updates in #LRM

(1) Deep Tabular Research via Continual Experience-Driven Execution
(2) Limited Reasoning Space: The cage of long-horizon reasoning in LLMs
(3) Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning

🔍 More at researchtrend.ai/communities/LRM

[2026-03-13] 📚 Updates in #VLM

(1) Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction
(2) Generalizing Vision-Language Models with Dedicated Prompt Guidance

🔍 More at researchtrend.ai/communities/VLM

[2026-03-13] 📚 Updates in #AI4CE

(1) On the Value of Tokeniser Pretraining in Physics Foundation Models

🔍 More at researchtrend.ai/communities/AI4CE

[2026-03-13] 📚 Updates in #AAML

(1) Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction
(2) Partially Recentralization Softmax Loss for Vision-Language Models Robustness

🔍 More at researchtrend.ai/communities/AAML

[2026-03-13] 📚 Updates in #DiffM

(1) TextFlux: An OCR-Free DiT Model for High-Fidelity Multilingual Scene Text Synthesis
(2) Distribution estimation via Flow Matching with Lipschitz guarantees

🔍 More at researchtrend.ai/communities/DiffM

[2026-03-13] 📚 Updates in #VGen

(1) V2A-DPO: Omni-Preference Optimization for Video-to-Audio Generation
(2) V2A-DPO: Omni-Preference Optimization for Video-to-Audio Generation

🔍 More at researchtrend.ai/communities/VGen

[2026-03-13] 📚 Updates in #OffRL

(1) Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning
(2) Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning

🔍 More at researchtrend.ai/communities/OffRL

[2026-03-13] 📚 Updates in #AI4TS

(1) Structure-Aware Set Transformers: Temporal and Variable-Type Attention Biases for Asynchronous Clinical Time Series

🔍 More at researchtrend.ai/communities/AI4TS

[2026-03-13] 📚 Updates in #LLMAG

(1) Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards
(2) The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey

🔍 More at researchtrend.ai/communities/LLMAG

[2026-03-13] 📚 Updates in #MedIm

(1) Weakly Supervised Teacher-Student Framework with Progressive Pseudo-mask Refinement for Gland Segmentation

🔍 More at researchtrend.ai/communities/MedIm

[2026-03-13] 📚 Updates in #ELM

(1) CUAAudit: Meta-Evaluation of Vision-Language Models as Auditors of Autonomous Computer-Use Agents
(2) Scaling Laws for Educational AI Agents
(3) Scaling Laws for Educational AI Agents

🔍 More at researchtrend.ai/communities/ELM

[2026-03-13] 📚 Updates in #CML

(1) Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation
(2) Interventional Time Series Priors for Causal Foundation Models
(3) Interventional Time Series Priors for Causal Foundation Models

🔍 More at researchtrend.ai/communities/CML

[2026-03-13] 📚 Updates in #CLL

(1) Lifelong Imitation Learning with Multimodal Latent Replay and Incremental Adjustment
(2) A Simple Efficiency Incremental Learning Framework via Vision-Language Model with Nonlinear Multi-Adapters

🔍 More at researchtrend.ai/communities/CLL

[2026-03-13] 📚 Updates in #KELM

(1) Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models

🔍 More at researchtrend.ai/communities/KELM

[2026-03-13] 📚 Updates in #3DGS

(1) VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
(2) Mobile-GS: Real-time Gaussian Splatting for Mobile Devices
(3) Mobile-GS: Real-time Gaussian Splatting for Mobile Devices

🔍 More at researchtrend.ai/communities/3DGS

[2026-03-13] 📚 Updates in #FedML

(1) Client-Conditional Federated Learning via Local Training Data Statistics
(2) Client-Conditional Federated Learning via Local Training Data Statistics

🔍 More at researchtrend.ai/communities/FedML

[2026-03-13] 📚 Updates in #3DV

(1) CARROT: A Learned Cost-Constrained Retrieval Optimization System for RAG
(2) STONE Dataset: A Scalable Multi-Modal Surround-View 3D Traversability Dataset for Off-Road Robot Navigation

🔍 More at researchtrend.ai/communities/3DV

[2026-03-13] 📚 Updates in #MoE

(1) Expert Selections In MoE Models Reveal (Almost) As Much As Text
(2) Scaling Machine Learning Interatomic Potentials with Mixtures of Experts

🔍 More at researchtrend.ai/communities/MoE

[2026-03-13] 📚 Updates in #ReLM

(1) Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thought
(2) VisDoT : Enhancing Visual Reasoning through Human-Like Interpretation Grounding and Decomposition of Thought

🔍 More at researchtrend.ai/communities/ReLM

[2026-03-13] 📚 Updates in #LM&Ro

(1) Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning

🔍 More at researchtrend.ai/communities/LM&Ro

[2026-03-13] 📚 Updates in #LLMSV

(1) Temporal Straightening for Latent Planning
(2) Temporal Straightening for Latent Planning
(3) Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment

🔍 More at researchtrend.ai/communities/LLMSV

[2026-03-13] 📚 Updates in #RALM

(1) Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning
(2) Can Small Language Models Use What They Retrieve? An Empirical Study of Retrieval Utilization Across Model Scale

🔍 More at researchtrend.ai/communities/RALM

[2026-03-13] 📚 Updates in #MU

(1) Unlearning the Unpromptable: Prompt-free Instance Unlearning in Diffusion Models
(2) The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning

🔍 More at researchtrend.ai/communities/MU

[2026-03-13] 📚 Updates in #CoGe

(1) Disentangled Representation Learning through Unsupervised Symmetry Group Discovery
(2) Disentangled Representation Learning through Unsupervised Symmetry Group Discovery

🔍 More at researchtrend.ai/communities/CoGe

[2026-03-13] 📚 Updates in #AuLLM

(1) Audio-Language Models for Audio-Centric Tasks: A Systematic Survey
(2) Resurfacing Paralinguistic Awareness in Large Audio Language Models
(3) Resurfacing Paralinguistic Awareness in Large Audio Language Models

🔍 More at researchtrend.ai/communities/AuLLM

[2026-03-13] 📚 Updates in #3DPC

(1) GGPT: Geometry Grounded Point Transformer
(2) GGPT: Geometry Grounded Point Transformer
(3) Zero-Shot Cross-City Generalization in End-to-End Autonomous Driving: Self-Supervised versus Supervised Representations

🔍 More at researchtrend.ai/communities/3DPC

[2026-03-13] 📚 Updates in #LM&MA

(1) Audio-Language Models for Audio-Centric Tasks: A Systematic Survey
(2) Audio-Language Models for Audio-Centric Tasks: A Systematic Survey
(3) Large Language Models for Biomedical Article Classification

🔍 More at researchtrend.ai/communities/LM&MA

[2026-03-13] 📚 Updates in #ALM

(1) Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning
(2) Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks

🔍 More at researchtrend.ai/communities/ALM

[2026-03-13] 📚 Updates in #MQ

(1) Quantized Inference for OneRec-V2
(2) Quantized Inference for OneRec-V2
(3) LongFlow: Efficient KV Cache Compression for Reasoning M
(4) LongFlow: Efficient KV Cache Compression for Reasoning M

🔍 More at researchtrend.ai/communities/MQ

[2026-03-13] 📚 Updates in #AILaw

(1) Legal-DC: Benchmarking Retrieval-Augmented Generation for Legal Documents
(2) Legal-DC: Benchmarking Retrieval-Augmented Generation for Legal Documents

🔍 More at researchtrend.ai/communities/AILaw