What do Language Models Learn and When? The Implicit Curriculum Hypothesis
Paper • 2604.08510 • Published • 3
M Saad Salman
MSS444
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
What do Language Models Learn and When? The Implicit Curriculum Hypothesis upvoted a paper 1 day ago
Self-Sovereign Agent upvoted a paper 1 day ago
Dive into Claude Code: The Design Space of Today's and Future AI Agent SystemsOrganizations
None yet
upvoted 5
papers 1 day ago
Self-Sovereign Agent
Paper • 2604.08551 • Published • 5
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Paper • 2604.14228 • Published • 13
LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
Paper • 2604.14922 • Published • 5
How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
Paper • 2604.14164 • Published • 23
upvoted 15
papers 3 days ago
CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation
Paper • 2604.09746 • Published • 1
You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
Paper • 2604.10966 • Published • 10
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
Paper • 2604.13010 • Published • 10
BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation
Paper • 2604.09497 • Published • 28
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
Paper • 2604.12374 • Published • 29
Toward Autonomous Long-Horizon Engineering for ML Research
Paper • 2604.13018 • Published • 31
KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance
Paper • 2604.12627 • Published • 96
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Paper • 2604.13016 • Published • 77
ROSE: Retrieval-Oriented Segmentation Enhancement
Paper • 2604.14147 • Published • 2
Do AI Coding Agents Log Like Humans? An Empirical Study
Paper • 2604.09409 • Published • 3
SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering
Paper • 2604.11548 • Published • 18
TIP: Token Importance in On-Policy Distillation
Paper • 2604.14084 • Published • 11
From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space
Paper • 2604.14142 • Published • 26
Target Policy Optimization
Paper • 2604.06159 • Published • 22
Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure
Paper • 2604.11045 • Published • 23