InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis
Paper • 2604.13201 • Published • 1
Joakim Lee
Reinforcement4All
AI & ML interests
None yet
Recent Activity
upvoted a paper about 12 hours ago
InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis upvoted a paper about 12 hours ago
MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments upvoted a paper about 12 hours ago
SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness EngineeringOrganizations
None yet
upvoted 20
papers about 12 hours ago
MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments
Paper • 2604.13418 • Published • 5
SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering
Paper • 2604.11548 • Published • 15
Target Policy Optimization
Paper • 2604.06159 • Published • 19
From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space
Paper • 2604.14142 • Published • 23
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models
Paper • 2604.10866 • Published • 46
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments
Paper • 2604.14144 • Published • 60
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time
Paper • 2604.11626 • Published • 95
Seedance 2.0: Advancing Video Generation for World Complexity
Paper • 2604.14148 • Published • 110
PokeRL: Reinforcement Learning for Pokemon Red
Paper • 2604.10812 • Published • 2
Parcae: Scaling Laws For Stable Looped Language Models
Paper • 2604.12946 • Published • 3
VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization
Paper • 2604.12887 • Published • 4
Accelerating Speculative Decoding with Block Diffusion Draft Trees
Paper • 2604.12989 • Published • 5
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
Paper • 2604.13010 • Published • 8
Generative Refinement Networks for Visual Synthesis
Paper • 2604.13030 • Published • 8
Rethinking the Diffusion Model from a Langevin Perspective
Paper • 2604.10465 • Published • 12
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
Paper • 2604.14025 • Published • 11
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting
Paper • 2604.12626 • Published • 13
Many-Tier Instruction Hierarchy in LLM Agents
Paper • 2604.09443 • Published • 14
Towards Long-horizon Agentic Multimodal Search
Paper • 2604.12890 • Published • 16