10 papers
VSPO: Vector-Steered Policy Optimization for Behavioral Control
Xuechen Zhang, Zijian Huang, Kai Yang +3
Modern language models often need to optimize a primary accuracy objective while also accommodating secondary behavioral preferences, such as verbosity, agreeableness, or the level…
Enabling Intrinsic Reasoning over Dense Geospatial Embeddings with DFR-Gemma
Xuechen Zhang, Aviv Slobodkin, Joydeep Paul +4
Representation learning for geospatial and spatio-temporal data plays a critical role in enabling general-purpose geospatial intelligence. Recent geospatial foundation models, such…
Continuous Chain of Thought Enables Parallel Exploration and Reasoning
Halil Alperen Gozeten, M. Emrullah Ildiz, Xuechen Zhang +3
Modern language models generate chain-of-thought traces by autoregressively sampling tokens from a finite vocabulary. While this discrete sampling has achieved remarkable success,…
Test-Time Training Provably Improves Transformers as In-context Learners
Halil Alperen Gozeten, M. Emrullah Ildiz, Xuechen Zhang +3
Test-time training (TTT) methods explicitly update the weights of a model to adapt to the specific test instance, and they have found success in a variety of settings, including mo…
SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
Xuechen Zhang, Koustava Goswami, Samet Oymak +2
Retrieval-augmented generation (RAG) has strong potential for producing accurate and factual outputs by combining language models (LMs) with evidence retrieved from large text corp…
BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
Xuechen Zhang, Zijian Huang, Yingcong Li +3
Small language models (SLMs) struggle to learn complex reasoning behaviors, especially when high-quality traces are scarce or difficult to learn from. The standard training approac…