Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
Paper • 2509.15591 • Published • 45
Papers that exist
-
-
A Survey on Latent Reasoning
Paper • 2507.06203 • Published • 94 -
Quantized Evolution Strategies: High-precision Fine-tuning of Quantized LLMs at Low-precision Cost
Paper • 2602.03120 • Published • 1 -
TADA! Tuning Audio Diffusion Models through Activation Steering
Paper • 2602.11910 • Published • 2 -
CoPE-VideoLM: Codec Primitives For Efficient Video Language Models
Paper • 2602.13191 • Published • 30 -
GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics
Paper • 2602.12617 • Published • 20 -
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
Paper • 2602.08683 • Published • 52 -
Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions
Paper • 2602.13013 • Published • 54 -
Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding
Paper • 2411.04282 • Published • 37 -
Latent Flow Transformer
Paper • 2505.14513 • Published • 29 -
LoRA-Drop: Temporal LoRA Decoding for Efficient LLM Inference
Paper • 2601.02569 • Published -
LLMs + Persona-Plug = Personalized LLMs
Paper • 2409.11901 • Published • 35 -
Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model
Paper • 2411.04496 • Published • 22 -
FoNE: Precise Single-Token Number Embeddings via Fourier Features
Paper • 2502.09741 • Published • 15 -
FLEXITOKENS: Flexible Tokenization for Evolving Language Models
Paper • 2507.12720 • Published • 10 -
Distilling Token-Trained Models into Byte-Level Models
Paper • 2602.01007 • Published -
Multiscale Byte Language Models -- A Hierarchical Architecture for Causal Million-Length Sequence Modeling
Paper • 2502.14553 • Published • 1 -
Byte Latent Transformer: Patches Scale Better Than Tokens
Paper • 2412.09871 • Published • 108 -
Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
Paper • 2505.11254 • Published • 48 -
Less is More: Recursive Reasoning with Tiny Networks
Paper • 2510.04871 • Published • 511 -
OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering
Paper • 2409.08250 • Published • 1 -
LightMem: Lightweight and Efficient Memory-Augmented Generation
Paper • 2510.18866 • Published • 115 -
The End of Manual Decoding: Towards Truly End-to-End Language Models
Paper • 2510.26697 • Published • 119 -
Kimi Linear: An Expressive, Efficient Attention Architecture
Paper • 2510.26692 • Published • 133 -
Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models
Paper • 2602.10224 • Published • 19 -
ProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented Generation
Paper • 2601.21912 • Published • 1 -
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
Paper • 2405.13792 • Published • 1 -
ReplaceMe: Network Simplification via Layer Pruning and Linear Transformations
Paper • 2505.02819 • Published • 26 -
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
Paper • 2502.16894 • Published • 32 -
DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing
Paper • 2602.12205 • Published • 80 -
MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling
Paper • 2602.11761 • Published • 7 -
CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
Paper • 2602.01766 • Published -
Elastic Attention: Test-time Adaptive Sparsity Ratios for Efficient Transformers
Paper • 2601.17367 • Published • 34 -
MemFly: On-the-Fly Memory Optimization via Information Bottleneck
Paper • 2602.07885 • Published • 7 -
Voxtral Realtime
Paper • 2602.11298 • Published • 19 -
UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory
Paper • 2602.10652 • Published • 3 -
Weight Decay Improves Language Model Plasticity
Paper • 2602.11137 • Published • 2 -
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
Paper • 2602.10229 • Published • 5 -
Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models
Paper • 2602.09713 • Published • 8 -
Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models
Paper • 2602.07106 • Published • 11 -
TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
Paper • 2602.08711 • Published • 28 -
How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning
Paper • 2602.10622 • Published • 27 -
Differential Transformer
Paper • 2410.05258 • Published • 182 -
Möbius Transform for Mitigating Perspective Distortions in Representation Learning
Paper • 2405.02296 • Published • 4 -
AToken: A Unified Tokenizer for Vision
Paper • 2509.14476 • Published • 37 -
Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
Paper • 2406.08085 • Published • 17 -
Badllama 3: removing safety finetuning from Llama 3 in minutes
Paper • 2407.01376 • Published -
RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning
Paper • 2406.10777 • Published • 2 -
OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models
Paper • 2406.01775 • Published • 3 -
RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions
Paper • 2501.00353 • Published -
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
Paper • 2603.12262 • Published • 30 -
Think While Watching: Online Streaming Segment-Level Memory for Multi-Turn Video Reasoning in Multimodal Large Language Models
Paper • 2603.11896 • Published • 8 -
WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
Paper • 2603.11593 • Published • 25 -
One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers
Paper • 2603.12245 • Published • 18 -
EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
Paper • 2603.12267 • Published • 13 -
OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams
Paper • 2603.12265 • Published • 12 -
Training Language Models via Neural Cellular Automata
Paper • 2603.10055 • Published • 7 -
Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data
Paper • 2603.07534 • Published • 5 -
FireRedASR2S: A State-of-the-Art Industrial-Grade All-in-One Automatic Speech Recognition System
Paper • 2603.10420 • Published • 6 -
NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks
Paper • 2603.06922 • Published • 2 -
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Paper • 2603.09229 • Published • 79 -
EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation
Paper • 2603.12108 • Published • 8 -
Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models
Paper • 2509.25162 • Published • 3 -
RecTok: Reconstruction Distillation along Rectified Flow
Paper • 2512.13421 • Published • 5 -
ε-VAE: Denoising as Visual Decoding
Paper • 2410.04081 • Published • 7 -
TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
Paper • 2412.03069 • Published • 34 -
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
Paper • 2502.14837 • Published • 3 -
Sparse-BitNet: 1.58-bit LLMs are Naturally Friendly to Semi-Structured Sparsity
Paper • 2603.05168 • Published • 4 -
Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning
Paper • 2602.23440 • Published • 3 -
BBQ-to-Image: Numeric Bounding Box and Qolor Control in Large-Scale Text-to-Image Models
Paper • 2602.20672 • Published • 9 -
LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model
Paper • 2603.01068 • Published • 22 -
NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing
Paper • 2603.02802 • Published • 7 -
InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions
Paper • 2603.03646 • Published • 8 -
Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
Paper • 2603.04257 • Published • 19 -
MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning
Paper • 2603.03379 • Published • 31 -
Proact-VL: A Proactive VideoLLM for Real-Time AI Companions
Paper • 2603.03447 • Published • 36 -
Helios: Real Real-Time Long Video Generation Model
Paper • 2603.04379 • Published • 173 -
Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations
Paper • 2603.01666 • Published • 1 -
WildActor: Unconstrained Identity-Preserving Video Generation
Paper • 2603.00586 • Published • 37 -
ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer
Paper • 2603.03583 • Published • 2 -
HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing
Paper • 2603.07236 • Published • 3 -
CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation
Paper • 2603.08652 • Published • 39 -
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
Paper • 2603.05890 • Published • 91 -
BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation
Paper • 2603.02816 • Published • 2 -
Towards a Neural Debugger for Python
Paper • 2603.09951 • Published • 5 -
Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs
Paper • 2603.09095 • Published • 28 -
Fish Audio S2 Technical Report
Paper • 2603.08823 • Published • 34 -
InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
Paper • 2603.09877 • Published • 47 -
UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations
Paper • 2603.10702 • Published • 4 -
According to Me: Long-Term Personalized Referential Memory QA
Paper • 2603.01990 • Published • 5 -
ID-LoRA: Identity-Driven Audio-Video Personalization with In-Context LoRA
Paper • 2603.10256 • Published • 19 -
HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration
Paper • 2603.07815 • Published • 10 -
OmniForcing: Unleashing Real-time Joint Audio-Visual Generation
Paper • 2603.11647 • Published • 31 -
Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation
Paper • 2603.12793 • Published • 37 -
MoKus: Leveraging Cross-Modal Knowledge Transfer for Knowledge-Aware Concept Customization
Paper • 2603.12743 • Published • 3 -
Attention Residuals
Paper • 2603.15031 • Published • 140 -
Test-Time Strategies for More Efficient and Accurate Agentic RAG
Paper • 2603.12396 • Published • 1 -
SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory
Paper • 2603.14588 • Published • 2 -
MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games
Paper • 2603.09022 • Published • 24 -
GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent
Paper • 2603.13875 • Published • 32 -
Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training
Paper • 2603.16139 • Published • 31