Model
Beat
News
Models
29
← Back to the timeline
Daily archive
Monday
— June 29, 2026
100 stories
— deduplicated across sources, ranked by significance, every source cited.
4
ReWorld: Learning Better Representations for World Action Models
Research
·
arXiv CS.AI
·
6h ago
A
4
Not All Relations Rotate Alike: Transformation-Aware Decoupling for Viewpoint-Robust 3D Scene Graph Generation
Research
·
arXiv CS.AI
·
6h ago
A
4
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
Research
·
arXiv CS.AI
·
6h ago
A
4
Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning
Research
·
arXiv CS.AI
·
6h ago
A
4
Fair Classification with Efficient and Post-hoc Controllable Fairness-Accuracy Trade-off
Research
·
arXiv CS.AI
·
6h ago
A
4
Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation
Products
·
arXiv CS.AI
·
6h ago
A
4
Fine-tuning a multimodal large language model for clinician-grade autism behavioral scoring from short home videos
Models
·
arXiv CS.AI
·
6h ago
A
4
Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching
Research
·
arXiv CS.AI
·
6h ago
A
4
AI-Driven Synthesis for High-Tech System Design: Automating Innovation
Research
·
arXiv CS.AI
·
6h ago
A
4
SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models
Models
·
arXiv CS.AI
·
6h ago
A
4
Diffusion Model Attribution via Spectral Coupling of Denoiser Responses
Research
·
arXiv CS.AI
·
6h ago
A
4
GeoFace: Consistent Multi-View Face Generation with Geometry-Constrained Diffusion
Research
·
arXiv CS.AI
·
6h ago
A
4
Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning
Research
·
arXiv CS.AI
·
6h ago
A
4
HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration
Research
·
arXiv CS.AI
·
6h ago
A
4
NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning
Models
·
arXiv CS.AI
·
6h ago
A
4
EntMTP: Accelerating LLM Inference with Entropy Guided Multi Token Prediction
Hardware
·
arXiv CS.AI
·
6h ago
A
4
Understanding How MLLMs Describe Artworks Using Token Activation Maps
Opinion
·
arXiv CS.AI
·
6h ago
A
4
ToxiREX: A Dataset on Toxic REasoning in ConteXt
Research
·
arXiv CS.AI
·
6h ago
A
4
MultiHashFormer: Hash-based Generative Language Models
Research
·
arXiv CS.AI
·
6h ago
A
4
Qwen-Image-2.0-RL Technical Report
Models
·
arXiv CS.AI
·
6h ago
A
4
Grounded Iterative Language Planning: How Parameterized World Models Reduce Hallucination Propagation in LLM Agents
Opinion
·
arXiv CS.AI
·
6h ago
A
4
Explainable AI for Biodiversity Monitoring and Ecological Image Analysis
Opinion
·
arXiv CS.AI
·
6h ago
A
4
From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models
Research
·
arXiv CS.AI
·
6h ago
A
4
When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search
Opinion
·
arXiv CS.AI
·
6h ago
A
4
Panoramic Scene Analysis: A Survey from Distortion-Aware Engineering to Sphere-Native Foundation Modeling
Opinion
·
arXiv CS.AI
·
6h ago
A
4
Verifiable Geometry Problem Solving: Solver-Driven Autoformalization and Theorem Proposing
Models
·
arXiv CS.AI
·
6h ago
A
4
Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control
Research
·
arXiv CS.AI
·
6h ago
A
4
Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment
Policy
·
arXiv CS.AI
·
6h ago
A
4
The Signal-Coverage Matrix: Stratifying Type and Semantic Errors in Statement Autoformalization
Models
·
arXiv CS.AI
·
6h ago
A
4
Output-Space Allocation Costs for Calibration-Guided LLM Compression: An Empirical Study
Research
·
arXiv CS.AI
·
6h ago
A
4
South Korea Unveils Plan to Sustain Lead in AI
Hardware
·
Bloomberg Technology
·
4h ago
B
4
Odyssey: Constructing Verifiable Local Truth-Preserving Foundation Models
Research
·
arXiv CS.AI
·
6h ago
A
4
Halt Fast! Early Stopping for Certified Robustness
Research
·
arXiv CS.AI
·
6h ago
A
4
The Curse of Multiple Mediators: Hidden Interaction Effects in Activation Patching
Models
·
arXiv CS.AI
·
6h ago
A
4
The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment
Research
·
arXiv CS.AI
·
6h ago
A
4
Masked Language Flow Models
Research
·
arXiv CS.AI
·
6h ago
A
4
Towards Automating Scientific Review with Google's Paper Assistant Tool
Research
·
arXiv CS.AI
·
6h ago
A
4
Tandem Reinforcement Learning with Verifiable Rewards
Research
·
arXiv CS.AI
·
6h ago
A
4
Vision-Default, Prior-Override: Causal Mechanisms of Perception-Knowledge Conflict in Vision-Language Models
Research
·
arXiv CS.AI
·
6h ago
A
4
Beyond MoCap: Scaling Motion Tokenizers with Synthetic Human Motion for Generative Modeling
Models
·
arXiv CS.AI
·
6h ago
A
4
Agentic Publication Protocol: An Attempt to Modernize Scientific Publication
Models
·
arXiv CS.AI
·
6h ago
A
4
Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework
Models
·
arXiv CS.AI
·
6h ago
A
4
Toward Robust In-Context Segmentation via Concept Guidance
Research
·
arXiv CS.AI
·
6h ago
A
4
ToE: A Hierarchical and Explainable Claim Verification Framework with Dynamic Multi-source Evidence Retrieval and Aggregation
Research
·
arXiv CS.AI
·
6h ago
A
4
Monocular Avatar Reconstruction via Cascaded Diffusion Priors and UV-Space Differentiable Shading
Research
·
arXiv CS.AI
·
6h ago
A
4
TruEye: Fine-Grained Detection of AI-Generated Human Subjects in Images
Research
·
arXiv CS.AI
·
6h ago
A
4
DMV-Bench: Diagnosing Long-Horizon Multimodal Agents' Visual Memory with Incidental Cue Injection
Research
·
arXiv CS.AI
·
6h ago
A
4
Aloe-Vision: Robust Vision-Language Models for Healthcare
Models
·
arXiv CS.AI
·
6h ago
A
4
German AI Rollout Offers €300 Billion Fix for Worker Shortage
Industry
·
Bloomberg Technology
·
5h ago
B
4
VASAE: Naming SAE Dictionary Directions with Vocabulary-Aligned Anchoring
Models
·
arXiv CS.AI
·
6h ago
A
4
ATOD: Annealed Turn-aware On-policy Distillation for Multi-turn Autonomous Agents
Policy
·
arXiv CS.AI
·
6h ago
A
4
Understanding Rollout Error in Graph World Models
Research
·
arXiv CS.AI
·
6h ago
A
4
TRUST: Efficient Abdominal Trauma Recognition via Image-to-Ultrasound-Video Transfer Learning
Research
·
arXiv CS.AI
·
6h ago
A
4
PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding
Research
·
arXiv CS.AI
·
6h ago
A
4
Learning to Reason with Curriculum II: Compositional Generalization
Models
·
arXiv CS.AI
·
6h ago
A
4
LLawCo: Learning Laws of Cooperation for Modeling Embodied Multi-Agent Behavior
Policy
·
arXiv CS.AI
·
6h ago
A
4
Position: The Term "Machine Unlearning" Is Overused in LLMs
Research
·
arXiv CS.AI
·
6h ago
A
4
Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs
Research
·
arXiv CS.AI
·
6h ago
A
4
Structured-Li-GS: Structured 3D Gaussians Splatting with LiDAR Incorporation and Spatial Constraints
Research
·
arXiv CS.AI
·
6h ago
A
4
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
Research
·
arXiv CS.AI
·
6h ago
A
4
Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling
Models
·
arXiv CS.AI
·
6h ago
A
4
AI-Generated Image Recognition via Fusion of CNNs and Vision Transformers
Research
·
arXiv CS.AI
·
6h ago
A
4
HybridCodec: Modeling Discrete and Continuous Representations for Efficient Speech Language Models
Research
·
arXiv CS.AI
·
6h ago
A
4
FoggyTrust: Robust Federated Learning with Hierarchical Trust Networks
Models
·
arXiv CS.AI
·
6h ago
A
4
Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding
Research
·
arXiv CS.AI
·
6h ago
A
4
What Was That Again? Certified Robustness for Automatic Speech Recognition
Opinion
·
arXiv CS.AI
·
6h ago
A
4
Perceptual 3D Simulation With Physical World Modeling
Research
·
arXiv CS.AI
·
6h ago
A
4
Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge
Research
·
arXiv CS.AI
·
6h ago
A
4
GNBAN: Graph Neural Basis Attention Networks for Long-Horizon Forecasting over Large Entity Sets
Policy
·
arXiv CS.AI
·
6h ago
A
4
Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents
Research
·
arXiv CS.AI
·
6h ago
A
4
FlexMoE: One-for-All Nested Intra-Expert Pruning for MoE Language Models
Research
·
arXiv CS.AI
·
6h ago
A
4
Latent Visual Diffusion Reasoning with Monte Carlo Tree Search
Research
·
arXiv CS.AI
·
6h ago
A
4
Unified Zero-Shot Time Series Forecasting: A Darts Foundation
Industry
·
arXiv CS.AI
·
6h ago
A
4
Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs
Models
·
arXiv CS.AI
·
6h ago
A
4
MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
Research
·
arXiv CS.AI
·
6h ago
A
4
Mitigating LLM-based p-Hacking by Preregistering for the Next LLM
Models
·
arXiv CS.AI
·
6h ago
A
4
Dangerous Liaisons of Convex Learning and Non-Affine Aggregation
Research
·
arXiv CS.AI
·
6h ago
A
4
The Simulacrum: Decision-Theoretic Pretraining for Near-Optimal Time-Series Forecasting and Inference
Research
·
arXiv CS.AI
·
6h ago
A
4
COOPA: A Modular LLM Agent Architecture for Operations Research Problems
Research
·
arXiv CS.AI
·
6h ago
A
4
PEBS: Per-rater Empirical-Bayes Shrinkage for RLHF Reward-Model Calibration
Models
·
arXiv CS.AI
·
6h ago
A
4
VLM-Aware Meta-Optic Front-End Design for Frozen Vision-Language Models
Research
·
arXiv CS.AI
·
6h ago
A
4
ModaFlow: Modality-Aware Flow Matching for High-Fidelity Virtual Try-On
Research
·
arXiv CS.AI
·
6h ago
A
4
DataStates-LLM: Scalable Checkpointing for Transformer Models Using Composable State Providers
Models
·
arXiv CS.AI
·
6h ago
A
4
Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation
Research
·
arXiv CS.AI
·
6h ago
A
4
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
Policy
·
arXiv CS.AI
·
6h ago
A
4
Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
Research
·
arXiv CS.AI
·
6h ago
A
4
How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks
Policy
·
arXiv CS.AI
·
6h ago
A
4
RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance
Policy
·
arXiv CS.AI
·
6h ago
A
4
Can LLMs Judge Better Than They Generate? Evaluating Task Asymmetry, Mechanistic Interpretability and Transferability for In-Context QA
Models
·
arXiv CS.AI
·
6h ago
A
4
Mechanism-Driven Monitors for Preemptive Detection of LLM Training Instability
Research
·
arXiv CS.AI
·
6h ago
A
4
JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications
Products
·
arXiv CS.AI
·
6h ago
A
4
Aurora: A Leverage-Aware Spectral Optimizer
Research
·
arXiv CS.AI
·
6h ago
A
4
TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
Models
·
arXiv CS.AI
·
6h ago
A
4
Flexformer: Flexible Linear Transformer with Learnable Attention Kernel
Research
·
arXiv CS.AI
·
6h ago
A
4
CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representations
Research
·
arXiv CS.AI
·
6h ago
A
4
When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning
Models
·
arXiv CS.AI
·
6h ago
A
4
HumanMoveVQA: Can Video MLLMs reason about human movement in videos?
Research
·
arXiv CS.AI
·
6h ago
A
4
Two-Stage Fine-Tuning for Protein Sequence Generation with Targeted Amino-Acid Composition
Models
·
arXiv CS.AI
·
6h ago
A
4
Are Time-Series Foundation Models Ready for E-Nose Data? An Empirical Assessment of Their Embeddings
Industry
·
arXiv CS.AI
·
6h ago
A
4
A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$
Research
·
arXiv CS.AI
·
6h ago
A
← Sun, Jun 28
Newer →