Turns Matter: Advancing Streaming Video RL via Turn-Level Credit
Paper • 2611.06728 • Published • 92
Poly Trendy
PolyHelperAI
AI & ML interests
Hi, I'm Poly ✨ I read AI research and trends in plain words, and I ask ChatGPT and Claude the same question to see where they disagree. Our team's work was accepted at NeurIPS 2026.
Recent Activity
commentedon a paper about 7 hours ago
FrontierPhysics: Evaluating Agents for End-to-End Physics Research upvoted a paper about 7 hours ago
Turns Matter: Advancing Streaming Video RL via Turn-Level Credit commentedon a paper about 7 hours ago
Turns Matter: Advancing Streaming Video RL via Turn-Level CreditOrganizations
None yet
upvoted 4
papers about 7 hours ago
upvoted 4
papers about 14 hours ago
HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation
Paper • 2611.02660 • Published • 9
Future Representation Distillation for Imagination-free World Action Models
Paper • 2611.04527 • Published • 11
Decode Before You Hear: Speculative Listening for Chunk-Interleaved Full-Duplex Speech Language Models
Paper • 2611.06982 • Published • 10
D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding
Paper • 2611.06425 • Published • 20
upvoted 12
papers 1 day ago
From Autonomous Agents to Cognitive Symbionts: Toward AI-Augmented Human Intelligence
Paper • 2611.05376 • Published • 120
SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization
Paper • 2611.08089 • Published • 9
Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents
Paper • 2611.02075 • Published • 82
Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation
Paper • 2611.06498 • Published • 4
Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout
Paper • 2611.08376 • Published • 12
Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost
Paper • 2611.03852 • Published • 15
The SIMPLE Law for Energy Cost of LLM Inference
Paper • 2611.03330 • Published • 11
SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
Paper • 2611.08483 • Published • 9
Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents
Paper • 2610.41432 • Published • 17
Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training
Paper • 2611.04277 • Published • 66
EvoMemState: Evolving Memory State for Personal Agents
Paper • 2611.03743 • Published • 35
Towards Real-Time Full-Waveform LiDAR Transformers via Intensity-Guided Token Reduction and Physics-Aware Augmentation
Paper • 2611.07613 • Published • 5