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 • 89 -
GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
Paper • 2604.26752 • Published • 108 -
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 • 13 -
Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention
Paper • 2605.22791 • Published • 31 -
Unsupervised Process Reward Models
Paper • 2605.10158 • Published • 26 -
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Paper • 2605.16928 • Published • 93 -
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 • 8 -
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 • 33 -
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards
Paper • 2605.31584 • Published • 41 -
Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
Paper • 2605.26844 • Published • 25 -
ESPO: Early-Stopping Proximal Policy Optimization
Paper • 2605.29860 • Published • 18 -
NITP: Next Implicit Token Prediction for LLM Pre-training
Paper • 2605.24956 • Published • 33 -
Self-Distilled Policy Gradient
Paper • 2606.04036 • Published • 18 -
MemTrain: Self-Supervised Context Memory Training
Paper • 2606.03197 • Published • 16 -
Latent Reasoning with Normalizing Flows
Paper • 2606.06447 • Published • 2 -
ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
Paper • 2606.03503 • Published • 24 -
Unified Neural Scaling Laws
Paper • 2605.26248 • Published • 7