AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation
Paper • 2602.17100 • Published • 3
COLLECTION
-
-
GroupGPT: A Token-efficient and Privacy-preserving Agentic Framework for Multi-User Chat Assistant
Paper • 2603.01059 • Published • 1 -
Multi-Domain Riemannian Graph Gluing for Building Graph Foundation Models
Paper • 2603.00618 • Published -
Heterogeneous Agent Collaborative Reinforcement Learning
Paper • 2603.02604 • Published • 186 -
Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory
Paper • 2603.04257 • Published • 19 -
InfinityStory: Unlimited Video Generation with World Consistency and Character-Aware Shot Transitions
Paper • 2603.03646 • Published • 8 -
TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods
Paper • 2407.21630 • Published • 8 -
SageBwd: A Trainable Low-bit Attention
Paper • 2603.02170 • Published • 17 -
Experiential Reinforcement Learning
Paper • 2602.13949 • Published • 71 -
On-Policy Self-Distillation for Reasoning Compression
Paper • 2603.05433 • Published • 6 -
Weak-Driven Learning: How Weak Agents make Strong Agents Stronger
Paper • 2602.08222 • Published • 283 -
Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs
Paper • 2602.10388 • Published • 243 -
Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning
Paper • 2511.16043 • Published • 110 -
LiteAttention: A Temporal Sparse Attention for Diffusion Transformers
Paper • 2511.11062 • Published • 32 -
KLASS: KL-Guided Fast Inference in Masked Diffusion Models
Paper • 2511.05664 • Published • 37 -
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
Paper • 2511.12710 • Published • 39 -
Virtual Width Networks
Paper • 2511.11238 • Published • 38 -
Distribution-Conditioned Transport
Paper • 2603.04736 • Published • 3 -
Truncated Step-Level Sampling with Process Rewards for Retrieval-Augmented Reasoning
Paper • 2602.23440 • Published • 3 -
Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling
Paper • 2603.04553 • Published • 3 -
Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model
Paper • 2603.05438 • Published • 39 -
Dynamic Chunking Diffusion Transformer
Paper • 2603.06351 • Published • 14 -
Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations
Paper • 2603.01666 • Published • 1 -
FlashPrefill: Instantaneous Pattern Discovery and Thresholding for Ultra-Fast Long-Context Prefilling
Paper • 2603.06199 • Published • 9 -
π-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs
Paper • 2603.02083 • Published • 9 -
EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding
Paper • 2603.04254 • Published • 1 -
LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding
Paper • 2602.20913 • Published • 11 -
Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns
Paper • 2602.22479 • Published -
VecGlypher: Unified Vector Glyph Generation with Language Models
Paper • 2602.21461 • Published • 12 -
Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
Paper • 2602.22647 • Published • 4 -
Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs
Paper • 2602.21198 • Published • 4 -
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
Paper • 2603.09906 • Published • 71 -
InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing
Paper • 2603.09877 • Published • 47 -
Towards a Neural Debugger for Python
Paper • 2603.09951 • Published • 5 -
TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery
Paper • 2603.08075 • Published -
ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning
Paper • 2603.05863 • Published • 5 -
Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control
Paper • 2603.09221 • Published -
Multi-Head Low-Rank Attention
Paper • 2603.02188 • Published • 3 -
Compiler-First State Space Duality and Portable O(1) Autoregressive Caching for Inference
Paper • 2603.09555 • Published • 1 -
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Paper • 2603.09229 • Published • 79 -
ReMix: Reinforcement routing for mixtures of LoRAs in LLM finetuning
Paper • 2603.10160 • Published • 25 -
Prism-Δ: Differential Subspace Steering for Prompt Highlighting in Large Language Models
Paper • 2603.10705 • Published • 11 -
OpenClaw-RL: Train Any Agent Simply by Talking
Paper • 2603.10165 • Published • 132 -
Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning
Paper • 2603.10377 • Published • 3 -
IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse
Paper • 2603.12201 • Published • 51 -
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
Paper • 2603.12180 • Published • 62 -
Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
Paper • 2603.12255 • Published • 90 -
CREATE: Testing LLMs for Associative Creativity
Paper • 2603.09970 • Published • 14 -
Geometric Autoencoder for Diffusion Models
Paper • 2603.10365 • Published • 6 -
Training Language Models via Neural Cellular Automata
Paper • 2603.10055 • Published • 7 -
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights
Paper • 2603.12228 • Published • 11 -
LifeGPT: Topology-Agnostic Generative Pretrained Transformer Model for Cellular Automata
Paper • 2409.12182 • Published -
Attention-based Neural Cellular Automata
Paper • 2211.01233 • Published -
HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration
Paper • 2603.07815 • Published • 10 -
Multimodal OCR: Parse Anything from Documents
Paper • 2603.13032 • Published • 31 -
LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
Paper • 2603.10899 • Published • 6 -
From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
Paper • 2603.12648 • Published • 12 -
VQQA: An Agentic Approach for Video Evaluation and Quality Improvement
Paper • 2603.12310 • Published • 7 -
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
Paper • 2602.14041 • Published • 53 -
ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces
Paper • 2602.11683 • Published • 8 -
Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning
Paper • 2602.11748 • Published • 31 -
The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies
Paper • 2602.09877 • Published • 197 -
MetaphorStar: Image Metaphor Understanding and Reasoning with End-to-End Visual Reinforcement Learning
Paper • 2602.10575 • Published • 4