UniBiDex: A Unified Teleoperation Framework for Robotic Bimanual Dexterous Manipulation

We present UniBiDex a unified teleoperation framework for robotic bimanual dexterous manipulation that supports both VRbased and leaderfollower input modalities UniBiDex enables realtime contactrich dualarm teleoperation by integrating heterogeneous input devices into a shared control stack with consistent kinematic treatment and safety guarantees The framework employs nullspace control to optimize bimanual configurations ensuring smooth collisionfree and singularityaware motion across tasks We validate UniBiDex on a longhorizon kitchentidying task involving five sequential manipulation subtasks demonstrating higher task success rates smoother trajectories and improved robustness compared to strong baselines By releasing all hardware and software components as opensource we aim to lower the barrier to collecting largescale highquality human demonstration datasets and accelerate progress in robot learning.

Turn-PPO: Turn-Level Advantage Estimation with PPO for Improved Multi-Turn RL in Agentic LLMs

Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. However, directly applying the widely used Group Relative Policy Optimization (GRPO) algorithm to multi-turn tasks exposes notable limitations, particularly in scenarios requiring long-horizon reasoning. To address these challenges, we investigate more stable and effective advantage estimation strategies, especially for multi-turn settings. We first explore Proximal Policy Optimization (PPO) as an alternative and find it to be more robust than GRPO. To further enhance PPO in multi-turn scenarios, we introduce turn-PPO, a variant that operates on a turn-level MDP formulation, as opposed to the commonly used token-level MDP. Our results on the WebShop and Sokoban datasets demonstrate the effectiveness of turn-PPO, both with and without long reasoning components.

HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices

Current multimodal large lanauge models possess strong perceptual and reasoning capabilities, however high computational and memory requirements make them difficult to deploy directly on on-device environments. While small-parameter models are progressively endowed with strong general capabilities, standard Vision Transformer (ViT) encoders remain a critical bottleneck, suffering from excessive latency and memory consumption when processing high-resolution inputs.To address these challenges, we introduce HyperVL, an efficient multimodal large language model tailored for on-device inference. HyperVL adopts an image-tiling strategy to cap peak memory usage and incorporates two novel techniques: (1) a Visual Resolution Compressor (VRC) that adaptively predicts optimal encoding resolutions to eliminate redundant computation, and (2) Dual Consistency Learning (DCL), which aligns multi-scale ViT encoders within a unified framework, enabling dynamic switching between visual branches under a shared LLM. Extensive experiments demonstrate that HyperVL achieves state-of-the-art performance among models of comparable size across multiple benchmarks. Furthermore, it significantly significantly reduces latency and power consumption on real mobile devices, demonstrating its practicality for on-device multimodal inference.

Kunlun Anomaly Troubleshooter: Enabling Kernel-Level Anomaly Detection and Causal Reasoning for Large Model Distributed Inference

Anomaly troubleshooting for large model distributed inference (LMDI) remains a critical challenge. Resolving anomalies such as inference performance degradation or latency jitter in distributed system demands significant manual efforts from domain experts, resulting in extremely time-consuming diagnosis processes with relatively low accuracy. In this paper, we introduce Kunlun Anomaly Troubleshooter (KAT), the first anomaly troubleshooting framework tailored for LMDI. KAT addresses this problem through two core innovations. First, KAT exploits the synchronicity and consistency of GPU workers, innovatively leverages function trace data to precisely detect kernel-level anomalies and associated hardware components at nanosecond resolution. Second, KAT integrates these detection results into a domain-adapted LLM, delivering systematic causal reasoning and natural language interpretation of complex anomaly symptoms. Evaluations conducted in Alibaba Cloud Service production environment indicate that KAT achieves over 0.884 precision and 0.936 recall in anomaly detection, providing detail anomaly insights that significantly narrow down the diagnostic scope and improve both the efficiency and success rate of troubleshooting.

BagIt! An Adaptive Dual-Arm Manipulation of Fabric Bags for Object Bagging

Bagging tasks, commonly found in industrial scenarios, are challenging considering deformable bags' complicated and unpredictable nature. This paper presents an automated bagging system from the proposed adaptive Structure-of-Interest (SOI) manipulation strategy for dual robot arms. The system dynamically adjusts its actions based on real-time visual feedback, removing the need for pre-existing knowledge of bag properties. Our framework incorporates Gaussian Mixture Models (GMM) for estimating SOI states, optimization techniques for SOI generation, motion planning via Constrained Bidirectional Rapidly-exploring Random Tree (CBiRRT), and dual-arm coordination using Model Predictive Control (MPC). Extensive experiments validate the capability of our system to perform precise and robust bagging across various objects, showcasing its adaptability. This work offers a new solution for robotic deformable object manipulation (DOM), particularly in automated bagging tasks. Video of this work is available at https://youtu.be/6JWjCOeTGiQ.

SpikingBrain Technical Report: Spiking Brain-inspired Large Models

Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing. Building large models on non-NVIDIA platforms also poses challenges for stable and efficient training. To address this, we introduce SpikingBrain, a family of brain-inspired models designed for efficient long-context training and inference. SpikingBrain leverages the MetaX GPU cluster and focuses on three aspects: (1) Model Architecture: linear and hybrid-linear attention architectures with adaptive spiking neurons; (2) Algorithmic Optimizations: an efficient, conversion-based training pipeline and a dedicated spike coding framework; (3) System Engineering: customized training frameworks, operator libraries, and parallelism strategies tailored to MetaX hardware. Using these techniques, we develop two models: SpikingBrain-7B, a linear LLM, and SpikingBrain-76B, a hybrid-linear MoE LLM. These models demonstrate the feasibility of large-scale LLM development on non-NVIDIA platforms. SpikingBrain achieves performance comparable to open-source Transformer baselines while using only about 150B tokens for continual pre-training. Our models significantly improve long-sequence training efficiency and deliver inference with (partially) constant memory and event-driven spiking behavior. For example, SpikingBrain-7B attains over 100x speedup in Time to First Token for 4M-token sequences. Training remains stable for weeks on hundreds of MetaX C550 GPUs, with the 7B model reaching a Model FLOPs Utilization of 23.4 percent. The proposed spiking scheme achieves 69.15 percent sparsity, enabling low-power operation. Overall, this work demonstrates the potential of brain-inspired mechanisms to drive the next generation of efficient and scalable large model design.

Handling Students Dropouts in an LLM-driven Interactive Online Course Using Language Models

Interactive online learning environments, represented by Massive AI-empowered Courses (MAIC), leverage LLM-driven multi-agent systems to transform passive MOOCs into dynamic, text-based platforms, enhancing interactivity through LLMs. This paper conducts an empirical study on a specific MAIC course to explore three research questions about dropouts in these interactive online courses: (1) What factors might lead to dropouts? (2) Can we predict dropouts? (3) Can we reduce dropouts? We analyze interaction logs to define dropouts and identify contributing factors. Our findings reveal strong links between dropout behaviors and textual interaction patterns. We then propose a course-progress-adaptive dropout prediction framework (CPADP) to predict dropouts with at most 95.4% accuracy. Based on this, we design a personalized email recall agent to re-engage at-risk students. Applied in the deployed MAIC system with over 3,000 students, the feasibility and effectiveness of our approach have been validated on students with diverse backgrounds.

Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation

Enabling humanoid robots to perform long-horizon mobile manipulation planning in real-world environments based on embodied perception and comprehension abilities has been a longstanding challenge. With the recent rise of large language models (LLMs), there has been a notable increase in the development of LLM-based planners. These approaches either utilize human-provided textual representations of the real world or heavily depend on prompt engineering to extract such representations, lacking the capability to quantitatively understand the environment, such as determining the feasibility of manipulating objects. To address these limitations, we present the Instruction-Augmented Long-Horizon Planning (IALP) system, a novel framework that employs LLMs to generate feasible and optimal actions based on real-time sensor feedback, including grounded knowledge of the environment, in a closed-loop interaction. Distinct from prior works, our approach augments user instructions into PDDL problems by leveraging both the abstract reasoning capabilities of LLMs and grounding mechanisms. By conducting various real-world long-horizon tasks, each consisting of seven distinct manipulatory skills, our results demonstrate that the IALP system can efficiently solve these tasks with an average success rate exceeding 80%. Our proposed method can operate as a high-level planner, equipping robots with substantial autonomy in unstructured environments through the utilization of multi-modal sensor inputs.

M-LLM Based Video Frame Selection for Efficient Video Understanding

Recent advances in Multi-Modal Large Language Models (M-LLMs) show promising results in video reasoning. Popular Multi-Modal Large Language Model (M-LLM) frameworks usually apply naive uniform sampling to reduce the number of video frames that are fed into an M-LLM, particularly for long context videos. However, it could lose crucial context in certain periods of a video, so that the downstream M-LLM may not have sufficient visual information to answer a question. To attack this pain point, we propose a light-weight M-LLM -based frame selection method that adaptively select frames that are more relevant to users' queries. In order to train the proposed frame selector, we introduce two supervision signals (i) Spatial signal, where single frame importance score by prompting a M-LLM; (ii) Temporal signal, in which multiple frames selection by prompting Large Language Model (LLM) using the captions of all frame candidates. The selected frames are then digested by a frozen downstream video M-LLM for visual reasoning and question answering. Empirical results show that the proposed M-LLM video frame selector improves the performances various downstream video Large Language Model (video-LLM) across medium (ActivityNet, NExT-QA) and long (EgoSchema, LongVideoBench) context video question answering benchmarks.

A$^2$ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization

Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache. Retrieval-based KV cache reduction methods can mitigate these challenges, typically by offloading the complete KV cache to CPU and retrieving necessary tokens on demand during inference. However, these methods still suffer from unsatisfactory accuracy degradation and extra retrieval overhead. To address these limitations, this paper proposes A$^2$ATS, a novel retrieval-based KV cache reduction method. A$^2$ATS aims to obtain an accurate approximation of attention scores by applying the vector quantization technique to key states, thereby enabling efficient and precise retrieval of the top-K tokens. First, we propose Windowed Rotary Position Embedding, which decouples the positional dependency from query and key states after position embedding. Then, we propose query-aware vector quantization that optimizes the objective of attention score approximation directly. Finally, we design the heterogeneous inference architecture for KV cache offloading, enabling long context serving with larger batch sizes. Experimental results demonstrate that A$^2$ATS can achieve a lower performance degradation with similar or lower overhead compared to existing methods, thereby increasing long context serving throughput by up to $2.7 \times$.