norfrun (✱,✱) ||

Axis Tech Update: From Action Replay to State Replay We've upgraded our backend replay mechanism from action replay to state replay. This can be summarized in 3 steps: - Record state (retain full info) - Compress representation (reduce cost) - Physics consistency validation (remove anomalies) Here is the research behind it: I. Action Replay Fails in Long Tasks Our goal was to enable zero-barrier web teleoperation of robots, seamlessly migrating data to servers for training and cross-sim replay. The pipeline spans multiple environments: User Browser (WASM) ➡️ Server Sim (Python MuJoCo) ➡️ Target Sim. Initially, we used Action Replay (recording commands and replaying them), but success rates dropped drastically as tasks got longer. II. The Root Cause: Underlying Differences in Simulators This error stems from the underlying heterogeneity across simulation environments. Different simulators have micro-differences in numerical precision, physics solver logic, time steps, and collision handling. In dynamical systems, these micro-errors are continuously amplified during time integration. State evolution is recursive: [Current State + Current Action ➡️ Next State]. A tiny deviation early on shifts the contact point, altering collision feedback. Eventually, the trajectory branches off irreversibly. Meaning: The same actions don't yield the same results across different sims. Relying solely on action sequences cannot guarantee reproducible physical trajectories. III. State Replay and New Challenges We shifted our paradigm to State Replay. Instead of recording "what actions were executed," we record "what physical states the system actually experienced." By recording full environment snapshots and loading them during replay, we bypass re-calculating the causal chain. This brought 2 new challenges: 1️⃣ Data Volume: We redesigned data structures to compress 1s of trajectory to ≈ 1KB. 2️⃣ Cheating Risks: Users could fake intermediate trajectories (see our recent anti-bot update). To fix this, we introduced Physical Consistency Validation. The physics engine acts as a referee, enforcing strict constraints: Extract [State + Action] ➡️ Run 1 server sim step ➡️ Get predicted state ➡️ Compare with recorded state. If the error exceeds the threshold, it's rejected. IV. A Higher-Level Perspective: A Denoising Problem From a higher perspective, cross-sim replay actually deals with noisy trajectory data (Real Trajectory + Cross-Sim Error). Our goal is to restore a physically consistent trajectory despite these inherent errors. We accept the inevitable biases between different simulators. Through state recording, compressed representation, and step-by-step physics validation, Axis guarantees trustworthy results. 🔵 To visualize the impact of this upgrade, check out the performance breakdown below. The table compares the success rates of Action Replay vs. State Replay across various tasks.

Ngày xưa dca $STRK hold all airdrop + mua thêm. Trên sàn cỡ còn 30k $STRK nữa :)) Mua cũng nhiều. Đợt 0.8 về bờ tiền mua + dca cơ mà không bán sau về Zero :)) đớn đau

Axis Anti-Bot Update Data quality is our absolute bottom line. At Axis, we are building the foundational dataset for physical AI, and we are committed to ensuring a fair environment where the efforts of real contributors are protected and rewarded. Recently, system monitoring and community feedback revealed cheating activities. Some users were reverse-engineering task conditions to directly forge trajectories, severely compromising data purity. To stop this, we implemented a strict Replay Logic in our backend. Last week, we launched a brand-new data format with expanded scene dimensions for precise physical replay, deliberately leaving a 3-day buffer for frontend cache updates. Despite this, our monitors showed that around 5% of wallets continued to submit faked, old-format data. While 5% seems small, their bots rapidly drained available task slots, stealing opportunities from real users. Following a comprehensive data backtrack, we have locked onto these wallets. They are now permanently banned, and all their occupied slots are being instantly reopened to genuine contributors. We also noticed early signs of a few genuine users experimenting with these exploits. Consider this a formal warning: we are letting it pass this time, but moving forward, any cheating attempts will result in an immediate and permanent ban. We will keep iterating our anti-cheat algorithms to protect our fair, high-quality ecosystem. Thank you to the majority of our community for your authentic supports. Below is a google sheet containing the list of banned addresses👇