Selected work

Representative Papers

Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents

Jul 09, 2026

Existing vision-language-action (VLA) models exhibit limited generalization under perturbations such as semantic re-targeting, object re-binding, layout changes, and unstable contacts, while purely analytical primitives struggle with irregular grasps and complex interactions. This work proposes a memory-augmented agent framework that decouples a frozen VLA—used as a retry-capable primitive for contact-intensive manipulation—from a small set of fixed analytical primitives. A memory-guided planner handles non-contact phases and semantic re-localization, invoking the VLA only during localized contact stages. The system learns the applicability boundaries of each primitive through execution trajectories, success heuristics, and failure models, thereby extending the VLA’s capabilities without fine-tuning. The approach outperforms the strongest baseline by 38.6 and 25.4 percentage points on LIBERO-Pro and RoboCasa365, respectively, and achieves a 58.4% success rate on RoboTwin C2R.

0 citationsRead paper

STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning

Jun 29, 2026

This work addresses the challenge in real-world robot learning where demonstration and interaction data often contain stalls, errors, and suboptimal behaviors, lacking a reliable frame-level signal to discern task progress. The authors propose STEAM, the first method to enable label-free, frame-level advantage modeling by training an ensemble of temporal offset predictors on expert trajectories. Normalized temporal offsets serve as a self-supervised signal, which is transformed into scalar advantage estimates via the ensemble’s predictive distribution, with conservative evaluation achieved through the ensemble minimum. Integrated with CFGRL policy optimization, STEAM significantly improves policy success rates by 59%, 54.3%, 23%, and 16.2% on real-world tasks including bimanual towel folding, chip checkout, cola restocking, and single-arm pick-and-place, effectively identifying and suppressing degenerate behaviors.

0 citationsRead paper

ReMP: Low-Downtime Runtime Model-Parallelism Reconfiguration for LLM Serving

Jun 17, 2026

Current large language model inference systems lack the capability to dynamically adjust model parallelism topologies at runtime, necessitating service restarts under varying workloads and causing multi-minute disruptions, loss of KV cache, and substantial recomputation overhead. This work proposes ReMP, the first framework enabling online elastic reconfiguration of combined tensor and pipeline parallelism. By decoupling topology from execution state, designing a two-dimensional KV cache migration mechanism, and orchestrating an end-to-end reconfiguration pipeline, ReMP reduces topology switching latency to 1–7 seconds across 7B–70B models—orders of magnitude faster than restarting. This significantly improves time-to-first-token (TTFT), time per output token (TPOT), and throughput under dynamic workloads.

0 citationsRead paper

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies

Jun 14, 2026

This work addresses the challenge that existing vision-language-action models struggle to explicitly predict scene dynamics induced by actions, while conventional world models rely on computationally expensive pixel-level video generation. To overcome this limitation, the authors propose LaWAM (Latent World Action Model), which for the first time integrates the latent space of pretrained vision foundation models with action-conditioned dynamics modeling. By leveraging lightweight latent dynamic prediction and compact latent visual subgoals to guide policy learning, LaWAM enables efficient and dynamics-aware robotic control. The method achieves state-of-the-art performance on the LIBERO (98.6%) and RoboTwin (91.22%) benchmarks as well as in real-world tasks, with a single action prediction requiring only 187 milliseconds—reducing latency by up to 24× compared to pixel-level world models.

0 citationsRead paper

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Jun 10, 2026

Existing general-purpose agents, such as OpenClaw, cannot be fairly evaluated for code generation due to their incompatibility with SWE-bench’s standardized evaluation protocol—including requirements like Dockerized workspaces and patch formatting. To address this, this work introduces Claw-SWE-Bench, a multilingual, standardized benchmark platform that enables fair comparison of heterogeneous agent adapters (claws) through unified prompting, runtime budgets, workspace contracts, patch extraction, and evaluation pipelines. For the first time, adapter design and API cost are incorporated as first-class dimensions in SWE task evaluation. The benchmark is built on a multilingual dataset of GitHub repair instances and employs cost- and rank-aware sampling strategies. Evaluated on 350 instances, a full adapter boosts OpenClaw’s Pass@1 from 19.1% to 73.4%, with model and adapter choices accounting for performance differences of 29.4 and 27.4 percentage points, respectively, alongside substantial variation in API costs.

0 citationsRead paper

Recent publications

Latest Papers

Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents

Jul 09, 2026

Existing vision-language-action (VLA) models exhibit limited generalization under perturbations such as semantic re-targeting, object re-binding, layout changes, and unstable contacts, while purely analytical primitives struggle with irregular grasps and complex interactions. This work proposes a memory-augmented agent framework that decouples a frozen VLA—used as a retry-capable primitive for contact-intensive manipulation—from a small set of fixed analytical primitives. A memory-guided planner handles non-contact phases and semantic re-localization, invoking the VLA only during localized contact stages. The system learns the applicability boundaries of each primitive through execution trajectories, success heuristics, and failure models, thereby extending the VLA’s capabilities without fine-tuning. The approach outperforms the strongest baseline by 38.6 and 25.4 percentage points on LIBERO-Pro and RoboCasa365, respectively, and achieves a 58.4% success rate on RoboTwin C2R.

0 citationsRead paper

STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning

Jun 29, 2026

This work addresses the challenge in real-world robot learning where demonstration and interaction data often contain stalls, errors, and suboptimal behaviors, lacking a reliable frame-level signal to discern task progress. The authors propose STEAM, the first method to enable label-free, frame-level advantage modeling by training an ensemble of temporal offset predictors on expert trajectories. Normalized temporal offsets serve as a self-supervised signal, which is transformed into scalar advantage estimates via the ensemble’s predictive distribution, with conservative evaluation achieved through the ensemble minimum. Integrated with CFGRL policy optimization, STEAM significantly improves policy success rates by 59%, 54.3%, 23%, and 16.2% on real-world tasks including bimanual towel folding, chip checkout, cola restocking, and single-arm pick-and-place, effectively identifying and suppressing degenerate behaviors.

0 citationsRead paper

ReMP: Low-Downtime Runtime Model-Parallelism Reconfiguration for LLM Serving

Jun 17, 2026

Current large language model inference systems lack the capability to dynamically adjust model parallelism topologies at runtime, necessitating service restarts under varying workloads and causing multi-minute disruptions, loss of KV cache, and substantial recomputation overhead. This work proposes ReMP, the first framework enabling online elastic reconfiguration of combined tensor and pipeline parallelism. By decoupling topology from execution state, designing a two-dimensional KV cache migration mechanism, and orchestrating an end-to-end reconfiguration pipeline, ReMP reduces topology switching latency to 1–7 seconds across 7B–70B models—orders of magnitude faster than restarting. This significantly improves time-to-first-token (TTFT), time per output token (TPOT), and throughput under dynamic workloads.

0 citationsRead paper

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies

Jun 14, 2026

This work addresses the challenge that existing vision-language-action models struggle to explicitly predict scene dynamics induced by actions, while conventional world models rely on computationally expensive pixel-level video generation. To overcome this limitation, the authors propose LaWAM (Latent World Action Model), which for the first time integrates the latent space of pretrained vision foundation models with action-conditioned dynamics modeling. By leveraging lightweight latent dynamic prediction and compact latent visual subgoals to guide policy learning, LaWAM enables efficient and dynamics-aware robotic control. The method achieves state-of-the-art performance on the LIBERO (98.6%) and RoboTwin (91.22%) benchmarks as well as in real-world tasks, with a single action prediction requiring only 187 milliseconds—reducing latency by up to 24× compared to pixel-level world models.

0 citationsRead paper

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Jun 10, 2026

Existing general-purpose agents, such as OpenClaw, cannot be fairly evaluated for code generation due to their incompatibility with SWE-bench’s standardized evaluation protocol—including requirements like Dockerized workspaces and patch formatting. To address this, this work introduces Claw-SWE-Bench, a multilingual, standardized benchmark platform that enables fair comparison of heterogeneous agent adapters (claws) through unified prompting, runtime budgets, workspace contracts, patch extraction, and evaluation pipelines. For the first time, adapter design and API cost are incorporated as first-class dimensions in SWE task evaluation. The benchmark is built on a multilingual dataset of GitHub repair instances and employs cost- and rank-aware sampling strategies. Evaluated on 350 instances, a full adapter boosts OpenClaw’s Pass@1 from 19.1% to 73.4%, with model and adapter choices accounting for performance differences of 29.4 and 27.4 percentage points, respectively, alongside substantial variation in API costs.

0 citationsRead paper