Mechanism-Guided Selective Unlearning for RLVR-Induced Reasoning

We propose MAST (Mechanism-Aligned Selective Targeting), a mechanism-guided method for unlearning RLVR-induced reasoning with substantially lower collateral damage than standard full-parameter updates. In matched SFT/RLVR checkpoints on Qwen2.5-Math-1.5B and Qwen3-1.7B-Base, the SFT-to-RLVR increment differs sharply from the SFT update in token-level delta-log-probability, and full-parameter gradient ascent forgets only by damaging retain MATH and GSM8K. MAST ranks attention-projection tensors by off-principal energy, update magnitude, and forget-gradient coupling magnitude, then updates only the top-ranked subset. On the primary model, MAST induces statistically significant target forgetting (MATH forget 45/150 to 37/150; McNemar p=0.0078) while preserving GSM8K (+0.8 pp) and MATH retain (-0.5 pp). The advantage reproduces across seeds, NPO/SimNPO objectives, and Qwen3, where MAST preserves GSM8K while full-parameter unlearning collapses it.

Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-Language Models

Fine-tuning vision-language models to emit dense coordinate lists improves visual grounding but also changes how models serialize, repeat, and terminate structured outputs. We study this behavior as a generation and control surface. In Gemma 4 12B, high-capacity q/k/v/o LoRA raises class-aware F1@0.3 from 0.007 to 0.448 while inducing repeated-tail pressure (duplicate rate 0.080, max repeat 23). A q/v rank sweep keeps max repeat at 21-22 across ranks 4-64, showing capacity persistence. The target signal is separable: object-level repeat-stop removes exact repeated records (duplicate rate 0.000, max repeat 1) while preserving F1 (0.494 to 0.490) and stricter F1@0.5 (0.381 to 0.385). Structure-axis probes localize the effect to bbox-coordinate object lists; dense non-bbox and spatial/count JSON remain repeat-clean, including under high-capacity adapters. Qwen3-VL-8B reproduces a clean controlled endpoint (F1@0.3 0.318, duplicate rate 0.000), and COCO 2017 reproduces acquisition plus duplicate pressure. Dense coordinate-list adaptation therefore creates a structure-bound, cross-family interference surface that can be measured and controlled.

The Vision Encoder as a Privacy Boundary: Visual-Token Side Channels in Encoder-Free Vision-Language Models

A vision encoder compresses image pixels into semantic embeddings, implicitly acting as a privacy boundary by preserving semantic content while attenuating pixel-local detail required for exact text recovery. Encoder-free vision-language models (VLMs) remove this boundary by routing image patches directly into the language-model token stream, thereby exposing an architectural privacy attack surface: intermediate visual tokens become a pre-output side channel. Under a token-access adversary, decoders invert visual-token streams from two encoder-free VLMs, Gemma4 and Fuyu, recovering recognizable image structure and readable held-out access codes, whereas matched encoder-based controls localize target regions but recover no exact strings. Within-model ablations show that the operative factor is spatial sampling fidelity of the visual-token grid, especially character-direction sampling density, rather than token or value count. The leakage is not limited to exported tokens: Gemma4 layer-0 key-value cache tensors are directly invertible, placing the side channel within KV caches commonly persisted by production serving stacks for decoding efficiency. The attack survives clutter, realistic document degradation, and zero-shot transfer to public document images, and it resists value-level defenses such as additive noise and quantization. Effective mitigation must therefore reduce spatial sampling, making removal of the vision encoder a first-class privacy decision in VLM deployment.