Retentive Adaptation
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data
Announce Type: new Abstract: Vision-language models (VLMs) are powerful general-purpose reasoners, yet converting them into robot control policies (VLAs) is surprisingly difficult. The root cause is a two-fold gap: VLMs are trained on internet-scale images with language-understanding objectives, while VLAs must perceive robot scenes and predict motor actions. Fine-tuning a VLM directly on robot action data forces the model to cross both gaps at once -- the learning curve is steep and the...
When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer
arXiv:2606.05626v1 Announce Type: new Abstract: Machine-generated text (MGT) attribution aims to identify the specific generator responsible for a given text, thereby providing fine-grained evidence for model accountability and misuse investigation. As new large language models continue to emerge, attribution models must continuously incorporate new generators while preserving their ability to recognize previously seen ones. Prior works have shown that this lifelong MGT attribution setting...
Policy on the AI Exponential
Policy on the AI Exponential In one of the side plots to The Lord of the Rings, two of the Hobbits attempt to rouse Treebeard—a wise but ponderous sentient tree—to defend his forest from an army that is cutting it down. The problem is that Treebeard operates at a very different speed than the Hobbits. It takes him a full day simply to say hello to another tree, so getting him and his peers to act fast enough is nearly impossible.
MAAT: Multi-phase Adapter-Aware Targeted Unlearning
Announce Type: new Abstract: Machine unlearning evaluation is structurally skewed: Why-type questions, which probe causal and relational knowledge, comprise less than 0.06% of CounterFact, 0.6% of ZSRE, and less than 1.3% of TOFU, MUSE, and WMDP-Cyber. This near-zero representation means that methods that fail on causal knowledge can score highly in aggregate, and this failure is undetectable without balanced evaluation. We present 5WBENCH, a balanced 5,000-sample benchmark with 1,000...
Reusing Fusion-Time Spectral Reliability for Adaptive Fusion and Expert Routing in RGB-Infrared Object Detection
arXiv:2606.01173v1 Announce Type: new Abstract: RGB-infrared detectors typically discard the statistics generated during cross-modal fusion, leaving downstream modules unaware of whether the current interaction is reliable. We propose to extract a parameter-free, 7-dimensional spectral reliability descriptor -- summarizing band energy, amplitude ratio, phase consistency, and cross-modal correlation -- and to reuse it beyond the fusion stage. The descriptor drives both Spectral Reliability...
Homology-Preserving Dimensionality Reduction via Adaptive Mapper and Landmark Isomap
Announce Type: new Abstract: As data becomes increasingly central across engineering and scientific disciplines, effective visualization is essential for interpreting complex, high-dimensional structures. Dimensionality reduction techniques project high-dimensional data into lower dimensions while aiming to preserve structural properties such as pairwise distances and local neighborhoods. In this paper, we focus on improving homological preservation, that is, the retention of topological...
AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
Announce Type: new Abstract: Token selection is pivotal for effective LLM post-training. However, existing methods mostly rely on local heuristics and rarely formulate token selection as a principled valuation of individual response tokens.
Harnessing Streaming Video in the Wild
Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly required to process unbounded video streams in applications such as video-call assistants, live commentary, and embodied robots. An ideal streaming system should support proactive interaction, long-horizon memory, and real-time processing, while resting on a VLM backbone capable of handling diverse in-the-wild streaming tasks. However, existing VLMs excel at offline video understanding but fall short in streaming...
LLM Anonymization Against Agentic Re-Identification
arXiv:2605.30848v2 Announce Type: replace Abstract: Agentic LLMs with web search change the threat model for text anonymization: weak contextual cues can become cross-referenceable evidence for re-identification, yet those same details also carry downstream analytic value of the text. Existing defenses either remove explicit identifiers, perturb text for formal privacy, or test rewritten text against non-web inference models, leaving underexplored the operating region between resistance to...
LLM Anonymization Against Agentic Re-Identificatio
arXiv:2605.30848v1 Announce Type: new Abstract: Agentic LLMs with web search change the threat model for text anonymization: weak contextual cues can become cross-referenceable evidence for re-identification, yet those same details also carry downstream analytic value of the text. Existing defenses either remove explicit identifiers, perturb text for formal privacy, or test rewritten text against non-web inference models, leaving underexplored the operating region between resistance to...