Related papers: CRANE: Constrained Reasoning Injection for Code Ag…
Post-training alignment of large language models (LLMs) relies on large-scale human annotations guided by policy specifications that change over time. Cultural shifts, value reinterpretations, and regulatory or industrial updates make…
Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks…
Recent advancements in large language models have intensified the need for efficient and deployable models within limited inference budgets. Structured pruning pipelines have shown promise in token efficiency compared to training…
Language models trained on web-scale corpora risk memorizing and exposing sensitive information, prompting the need for effective machine unlearning. Prior methods mainly focus on input queries to suppress sensitive outputs, yet this often…
Although synthetic data is widely promoted as a remedy, its prevailing production paradigm -- one optimizing for statistical smoothness -- systematically removes the long-tail, cognitively grounded irregularities that characterize human…
Recent progress in large language models (LLMs) has been propelled by reinforcement learning with verifiable rewards (RLVR) and test-time scaling. However, the limited output length of LLMs constrains the depth of reasoning attainable in a…
Despite pre-trained language models have proven useful for learning high-quality semantic representations, these models are still vulnerable to simple perturbations. Recent works aimed to improve the robustness of pre-trained models mainly…
Existing reasoning data curation pipelines score whole samples, treating every intermediate step as equally valuable. In reality, steps within a trace contribute very unevenly, and selecting reasoning data well requires assessing them…
Test-time compute scaling has emerged as a powerful paradigm for enhancing mathematical reasoning in large language models (LLMs) by allocating additional computational resources during inference. However, current methods employ uniform…
Listwise reranking utilizing Large Language Models (LLMs) has achieved state-of-the-art retrieval effectiveness. Recently, reasoning-enhanced models have further pushed these boundaries by employing Chain-of-Thought (CoT) to perform deep…
Instruction-based image editing has emerged as a prominent research area, which, benefiting from image generation foundation models, have achieved high aesthetic quality, making instruction-following capability the primary challenge.…
Long chain-of-thought~(CoT) has become a dominant paradigm for enhancing the reasoning capability of large reasoning models~(LRMs); however, the performance gains often come with a substantial increase in reasoning budget. Recent studies…
Targeting the issues of "shortcuts" and insufficient contextual understanding in complex cross-modal reasoning of multimodal large models, this paper proposes a zero-shot multimodal reasoning component guided by human-like cognitive…
Hybrid reasoning language models are commonly controlled through high-level Think/No-think instructions to regulate reasoning behavior, yet we found that such mode switching is largely driven by a small set of trigger tokens rather than the…
Visual long-document understanding is critical for enterprise, legal, and scientific applications, yet the best performing open recipes have not explored reasoning, a capability which has driven leaps in math and code performance. We…
Reasoning language models such as DeepSeek-R1 produce long chain-of-thought traces during inference time which make them costly to deploy at scale. We show that using compression techniques such as neural network pruning produces greater…
Reinforcement learning substantially improves reasoning in large language models, but it also tends to lengthen chain of thought outputs and increase computational cost during both training and inference. Though length control methods have…
As agents based on large language models are increasingly deployed to long-horizon tasks, maintaining their alignment with stakeholder preferences becomes critical. Effective alignment in such settings requires reward models that are…
The Transformer architecture, despite its widespread success, struggles with long-context scenarios due to quadratic computation and linear memory growth. While various linear attention variants mitigate these efficiency constraints by…
A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while the task still completes. We call this overeager behavior: the prompt is not adversarial and…