We have 11 of 11 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
STP-GUI (Spatially-aware Token Pruning for GUI agents), a query-guided token pruning framework that preserves fine-grained instruction-conditioned token scoring while performing spatially coherent window-level selection under aggressive token reduction is proposed.
Visual backbones have evolved from Convolutional Neural Networks (CNNs) with local aggregation to Vision Transformers (ViTs) with global interactions, State-Space Models (SSMs) with input-dependent state transitions, and Test-Time Training (TTT) layers that adapt an inner learner while processing an image. Across this...
AR-WAM is presented, a visual-conditioned, agent-ready world action model that replaces language with two complementary conditions: a visual grounding prompt and a learnable operation token dictating the atomic skill to execute, predicting scene evolution within compact latent states while decoding actions.
UniOPSD (Unified On-Policy Self-Distillation) is introduced, which unifies these feedback sources through adaptive local credit arbitration and constructs comparable credit estimates from environmental returns and successful-peer hindsight at shared interaction anchors.
These results support accounting for selection history when constructing and evaluating search-agent rollouts and rank first on seven QA benchmarks using Qwen3-4B, Qwen3-8B, and Qwen2.5-7B.
Self-Supervised Skill Optimization (SSO) is introduced, a comparative framework that learns a reusable skill from unlabeled task instances alone and outperforms existing GT-free prompt optimizers on both closed-ended and open-ended tasks.
The results show that evolving skill memory is not merely an inference-time plug-in: it changes policy learning and the future training distribution while retaining value as optional external memory.
WebRetriever is introduced, a large-scale benchmark encompassing 800 websites and 1,550 tasks across diverse domains, including consumer, professional, and enterprise sectors, with comprehensive coverage of user intent patterns, and NavEval (Navigation Evaluation), a novel LLM-as-Judge framework that leverages rich int...
This work systematically characterize the implicit biases introduced by low-rank adaptation during alignment and establishes two theorems showing that low-rank alignment induces preferences for parameter subspaces with flat gradients and feature subspaces robust to perturbations, providing a principled explanation for...
LiLa-WAM is proposed, a lightweight world-action model that reasons about the future in a compact latent space and can be trained end-to-end on a single 24GB GPU and the Visual Transition Token (VTT), a language-free task representation that encodes each task as a direction in visual feature space.
CoEvoKG is introduced, a framework that turns a knowledge graph into both a source of verifiable training tasks and a persistent evidence memory for agent evolution, closing the loop between model self evolution and knowledge accumulation.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
