40 papers
Where Does Generative Difficulty Reside? An Empirical Study of Target Representations
Marcel Plocher, Bernhard Schölkopf, Andreas Geiger +1
The target representation defines the distribution an image generator must learn, yet it is often treated as an interchangeable interface. This assumption is particularly questiona…
How Does Alignment Tuning Shape Representations of Sycophancy and Related Cue-Induced Biases in LLMs?
Prakhar Gupta, Terry Jingchen Zhang, Florent Draye +2
Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant…
Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models
Moritz Miller, Florent Draye, Bernhard Schölkopf +1
A central premise in mechanistic interpretability is that meaningful concepts in language models are represented by linear features in activation space. For such features to suppor…
PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding
Duc Cao Dinh, Khai Le-Duc, Florent Draye +4
3D Visual Grounding (3DVG) aims to localize target objects in 3D scenes given natural language descriptions. Existing approaches typically perform reasoning over the entire scene,…
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR
Yongjin Yang, Jiarui Liu, Yinghui He +3
Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science.…
Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories
Merve Kocabas, Gege Gao, Bernhard Schölkopf +1
Diffusion and flow-based generative models produce strong images, yet their controllability remains largely endpoint-centric: users specify conditions and receive final outputs, wh…