Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation
Paper • 2608.05785 • Published • 5
Yury Panikov
panikov
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
Task-Conditional Flow Matching for Balanced Multilingual Text Embedding AdaptationOrganizations
None yet
upvoted 8
papers about 7 hours ago
FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds
Paper • 2608.01049 • Published • 6
Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
Paper • 2608.01851 • Published • 6
MASS: Multiplayer World Models with Authoritative Shared State
Paper • 2608.06257 • Published • 9
Invisible Shortcuts: Why Vision Encoders Know Your Camera
Paper • 2608.05424 • Published • 11
PaDoc: Layout-Grounded Parallel Decoding for Document Parsing
Paper • 2608.06146 • Published • 16
Continual Learning in Transition
Paper • 2608.06216 • Published • 14
KVAE: Family of Tokenizers for Multimodal Generative Models
Paper • 2608.05798 • Published • 15
upvoted 4
papers about 8 hours ago
Teaching Nemotron Greek: Mining a Corpus, Adapting Retrieval, and Grounding Generation for Modern Greek across Specialist Domains
Paper • 2608.05138 • Published • 24
On-Policy Delta Distillation for Multilingual Math Reasoning
Paper • 2608.05802 • Published • 24
DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces
Paper • 2608.03451 • Published • 26
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
Paper • 2608.06301 • Published • 28
upvoted 3
papers about 10 hours ago
From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models
Paper • 2608.06020 • Published • 28
ChronoVision: Temporal Reasoning via Latent State Reconstruction
Paper • 2608.05631 • Published • 33
Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval
Paper • 2608.06060 • Published • 32
upvoted 5
papers 1 day ago
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
Paper • 2608.06197 • Published • 35
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
Paper • 2607.28609 • Published • 61
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Paper • 2608.05987 • Published • 76
What AI Red-Team Evaluations Can and Cannot Prove
Paper • 2607.21735 • Published • 3
Self-Evolving Coding Agents
Paper • 2608.03392 • Published • 6