Entities · Models
Qwen3-4B
32 articles tagged with this entity.
-
Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
-
Geometry of Ordinal Representations in Language Models
-
Towards Inclusive Mobility Modeling: Characterizing and Evaluating Elderly Trajectory Patterns in Urban Systems
-
Discovering Millions of Interpretable Features with Sparse Autoencoders
-
Weight-Space Geometry of Offline Reasoning Training
-
Source-Grounded Data Generation for Text-to-JSON Learning
-
From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning
-
Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution
-
SMEPilot: Characterizing and Optimizing LLM Inference with Scalable Matrix Extensions
-
Operator Fusion for LLM Inference on the Tensix Architecture
-
Bittensor Agent Arenas as a Trajectory Primitive: Distilling a Shopping Agent from ShoppingBench Subnet Traces
-
Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models
-
HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
-
CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts
-
From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA Merging
-
COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
-
DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
-
Cost-Aware Diffusion Draft Trees for Speculative Decoding
-
ProtStructQA: A Denotation Threshold in Protein Structural Reasoning
-
ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose Reasoning Tasks
-
Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs
-
Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting
-
Playing with Words, Improving with Rewards: Training Language Models for Creative Association
-
ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay
-
VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization
-
Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning
-
ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling
-
Real-Time Progress Prediction in Reasoning Language Models
-
What Makes a Medical Checker Trainable? Diagnosing Signal Collapse and Reward Hacking in Checker-Guided RAG for Biomedical QA
-
DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory
-
Towards a Universal Causal Reasoner
-
Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates