Why Fine-Tuning Encourages Hallucinations and How to Fix It
Paper • 2604.15574 • Published • 25
toread
-
-
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
Paper • 2604.24763 • Published • 71 -
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
Paper • 2604.24819 • Published • 91 -
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
Paper • 2604.26752 • Published • 112 -
Large Language Models Explore by Latent Distilling
Paper • 2604.24927 • Published • 74 -
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
Paper • 2604.26779 • Published • 14 -
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
Paper • 2605.22791 • Published • 33 -
Unsupervised Process Reward Models
Paper • 2605.10158 • Published • 27 -
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Paper • 2605.16928 • Published • 97 -
From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
Paper • 2605.20177 • Published • 10 -
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
Paper • 2605.19282 • Published • 9 -
Channel-wise Vector Quantization
Paper • 2605.26089 • Published • 15 -
Negligible in Size, Significant in Effect: On Scale Vectors in Large Language Models
Paper • 2605.26895 • Published • 20 -
Task-Focused Memorization for Multimodal Agents
Paper • 2605.31075 • Published • 39 -
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
Paper • 2605.31584 • Published • 43 -
Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
Paper • 2605.26844 • Published • 26 -
ESPO: Early-Stopping Proximal Policy Optimization
Paper • 2605.29860 • Published • 20 -
NITP: Next Implicit Token Prediction for LLM Pre-training
Paper • 2605.24956 • Published • 35 -
Self-Distilled Policy Gradient
Paper • 2606.04036 • Published • 27 -
MemTrain: Self-Supervised Context Memory Training
Paper • 2606.03197 • Published • 17 -
Latent Reasoning with Normalizing Flows
Paper • 2606.06447 • Published • 8 -
ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
Paper • 2606.03503 • Published • 25 -
Unified Neural Scaling Laws
Paper • 2605.26248 • Published • 7 -
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings
Paper • 2606.07502 • Published • 97 -
On the Geometry of On-Policy Distillation
Paper • 2606.07082 • Published • 73 -
Dynamic Linear Attention
Paper • 2606.10650 • Published • 5 -
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
Paper • 2606.10646 • Published • 6 -
Rethinking the Divergence Regularization in LLM RL
Paper • 2606.09821 • Published • 33 -
Redesign Mixture-of-Experts Routers with Manifold Power Iteration
Paper • 2606.12397 • Published • 87 -
MiniMax Sparse Attention
Paper • 2606.13392 • Published • 146 -
Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
Paper • 2606.15007 • Published • 16 -
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
Paper • 2606.11176 • Published • 126 -
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Paper • 2606.12370 • Published • 21 -
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Paper • 2606.15079 • Published • 84 -
ExpRL: Exploratory RL for LLM Mid-Training
Paper • 2606.17024 • Published • 5 -
Variable-Width Transformers
Paper • 2606.18246 • Published • 15 -
Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients
Paper • 2606.18216 • Published • 61 -
Rethinking the Role of Efficient Attention in Hybrid Architectures
Paper • 2606.15378 • Published • 17 -
Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models
Paper • 2606.19750 • Published • 3 -
Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning
Paper • 2606.18831 • Published • 6 -
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
Paper • 2606.24937 • Published • 13 -
Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning
Paper • 2606.24133 • Published • 8