AI Model2026
An open-weight LLM focused on deep reasoning, native agentic tool use, and repository-scale code understanding — Mixture-of-Experts architecture with an extended context window and permissive licensing.
Embodied AI2026
Provides a portable, robot-free UMI capture pipeline and shows that policies post-trained only on this high-fidelity data deploy directly on real robots matching teleoperation baselines. Capture achieves ~3 mm end-effector accuracy, microsecond sync, ultra-wide FOV, and releases 2,000h HiFi-UMI-2K.
AI Video Papers2026
Converts text prompts into physically consistent videos by synthesizing executable Blender programs as a process-level chain-of-thought and using a dual-engine pipeline (deterministic simulation draft + draft-conditioned video editor). Ships with a VideoCoCo-3K draft–instruction–target dataset and shows substantial gains in physical-consistency benchmarks.
Directly maps visual observations and language instructions to continuous robot actions, replacing LLM-centric V→L→A pipelines. Uses separate visual and language encoders with lightweight bidirectional interaction and a compact decoder to cut inference cost and VRAM, achieving ~31 ms latency and <1 GB VRAM on an RTX 4090; suited for real-time robotic manipulation under tight compute budgets.
Autonomously proposes, modifies, executes, and evaluates ML experiments to study recursive self-improvement in machine learning engineering. Implements an open stack (OpenMLE-Gym, -RL, -Evo) and post-trains Frontis-MA1 (35B) around four evolution operators (Draft, Improve, Debug, Crossover); releases model weights and the full codebase.
AI Infra2026
Runs Kimi K3 inference on CPU by streaming model weights from storage instead of keeping them all in RAM. The project reports 8.24 GB peak memory, with substantially slower token generation at low-memory settings.
A pretrain-then-transfer method for streaming recommendation that decouples refreshable behavioral knowledge from task-specific geometry to enable continual model refresh without downstream interference; introduces Behavioral Multi-Token Prediction and Anchored Calibration Residual and shows 4–12% offline gains plus live Shopee A/B lifts.
Frames skill generation as a sequential editing task and introduces a novel rollback reward to train an RL generator (Skill-α) that evaluates each edit by its downstream execution impact, producing skills that improve agent success rates across document-to-skill and experience-to-skill settings.
Supervises audio reasoning by generating per-sample, audio-grounded rubrics that evolve with model rollouts and serve as reinforcement-learning rewards, improving perception and adaptive multi-step reasoning while avoiding reward saturation.
AI Agent Papers2026
Orchestrates reasoning, external tool use, and native image generation under one unified multimodal agent policy via post-training. Introduces RAD-GRPO for agentic reinforcement fine-tuning and releases training data plus the full post-training infrastructure.
Replaces external environment interaction in agentic RL training with 'world rehearsal': the policy alternates between making tool calls and simulating their environment responses, jointly optimizing both roles so the agent internalizes environment dynamics and improves long-horizon tool use and transfer.
AI Video Papers2026
Uses video generation only as a training signal to co-train a pretrained video expert and a lightweight action expert, then discards the video branch at inference to produce a low-latency end-to-end driving planner; enhanced with RL for compositional driving rewards.