The rapid proliferation of Large Language Models (LLMs) necessitates reliable watermarking techniques to identify AI-generated text and ensure appropriate attribution. While token-based watermarks are vulnerable to paraphrasing, a central challenge for semantic watermarking is to turn sentence meanings into a stable, w...
Results show that effective memory can be realized through a compact online state directly coupled with attention computation, without full fine-tuning, backbone replacement, or explicit context extension.
Jing-Di Lei, Di Zhang, Junxian Li et al.· arXiv.org· 10 citations
This work proposes $\delta$-Vision, which replaces repeated Transformer evolution of visual tokens with lightweight low-rank adapters that construct layer-wise visual memories while preserving all visual tokens for text retrieval, and achieves higher accuracy than visual token pruning baselines at comparable or lower c...
Jing-Di Lei, Junxian Li, Di Zhang et al.· 0 citations
BaRe-Mem, an online Bayesian reliability memory for multi-agent consultation, is introduced, an online Bayesian reliability memory for multi-agent consultation that estimates advisor reliability based on the central model's internal belief representations and updates these estimates from historical interactions.
Findings support MemBodied as a practical alternative to expanding the policy context for history-dependent manipulation, a fixed-size episodic memory with two complementary components: an associative state that records interactions across policy calls and an episode anchor that preserves a compact representation of th...
Tej Deep Pala, N. Majumder, Bryce Goh et al.· 0 citations
Genie Envisioner Act 2.0 (GE-Act 2.0) is introduced, a world-action model whose trainable generative and action components are all initialized from scratch on manipulation data, and its components are jointly trained with knowledge-aligned selective optimization (KASO), which reduces mismatched supervision.
AgiBot Research Team, Ren-Hang Liu, Wen-Zhi Zhao et al.· 4 citations· ⚡1
MnIST-PRO is addressed, a benchmark that isolates agentic perception by converting MNIST digit recognition into a sequential, glimpse-based search task with lookback constraints, and ten multimodal models are evaluated, showing that simply acquiring visual evidence is not enough and agents must also be able to build an...
Vernon Toh, N. Majumder, Zhengyuan Liu et al.· 0 citations
Memory is central to long-horizon LLM agents, yet existing memory systems primarily preserve interaction content rather than modeling which agents can be trusted and under what conditions. This limitation is particularly important in multi-agent systems, where a central model may be unable to directly verify plausible...
This work argues that research ideation should be treated as a conjunction of both objectives and framed as a Quality-Diversity (QD) search, and introduces IDEAgent, a multi-agent framework that manages the evolution of ideas through lineages.
ScrambleToolBench is introduced, an interactive terminal benchmark designed to isolate behavioral reasoning by removing semantic cues and enforcing a continuous task curriculum, which requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.
Vernon Toh, Navonil Majumder, Zhengyuan Liu et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
