…We introduce X2SAM, a unified segmentation MLLM that extends any-segmentation capabilities from images to videos. Given conversational instructions and visual prompts, X2SAM couples an LLM with a Mask Memory module that…
…AI-generated summary Most existing large language models (LLMs) are expensive to adapt after deployment, especially when a task requires newly produced information or niche domain knowledge. Recent work has shown that…
…AI-generated summary LLM/VLM-based digital agents have advanced rapidly thanks to scalable sandboxes for coding, web navigation, and computer use, which provide rich interactive training grounds. In contrast, embodied agents…
…Yangyi Huang , , , , , , Weiyang Liu Abstract Parameter-efficient fine-tuning methods exhibit varying stability-plasticity trade-offs in preserving pretrained capabilities, with orthogonal fine-tuning showing optimal performance under similar parameter constraints. AI…
…Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes Published on May 29 Submitted by Jie Feng on Jun 4 FIBLAB, Tsinghua University Authors: , Jie Feng , , , , , , , Abstract Vision-language…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Image generation models have evolved from text-conditioned pixel synthesis toward multimodal agents endowed with visual comprehension and tool invocation capabilities. Yet, existing agents…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and action generation. However, their ability to sustain exploration in dynamic open…
…AI-generated summary Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy , as training signals emerge only within its in-capability region…
…CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts (2026) CODESKILL: Learning Self-Evolving Skills for Coding Agents (2026) RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training…
…An Intrinsic Capability of Attention-Based Models Published on May 8 Submitted by Elad Hoffer on May 14 NVIDIA Authors: , , , , , Abstract INTRA demonstrates that attention-based models can perform retrieval directly from…