相关论文: Trust but Verify: Prover-Verifier Deliberation for…

Confident prediction is highly relevant in machine learning; for example, in applications such as medical diagnoses, wrong prediction can be fatal. For classification, there already exist procedures that allow to not classify data when the…

Large Vision Language Models (LVLMs) achieve strong multimodal reasoning but frequently exhibit hallucinations and incorrect responses with high certainty, which hinders their usage in high-stakes domains. Existing verbalized confidence…

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target model verifies. A critical hyperparameter in this process is the speculation length…

As large language models (LLMs) transition from research prototypes to production systems, practitioners often need reliable methods to verify model outputs and characterize tail risk for safe deployment. While sampling-based estimates…

Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a promising approach to improve correctness in LLMs, however, in many scientific problems, the objective is not necessarily to produce the correct answer, but instead to…

Voice activity detection (VAD) improves the performance of speaker verification (SV) by preserving speech segments and attenuating the effects of non-speech. However, this scheme is not ideal: (1) it fails in noisy environments or…

The DC-nets approach to anonymity has long held attraction for its strength against traffic analysis, but practical implementations remain vulnerable to internal disruption or "jamming" attacks requiring time-consuming tracing procedures to…

Recently, a plethora of works have proposed inference-time algorithms (e.g. best-of-n), which incorporate verifiers to assist the generation process. Their quality-efficiency trade-offs have been empirically benchmarked on a variety of…

In large language model (LLM) agents, reasoning trajectories are treated as reliable internal beliefs for guiding actions and updating memory. However, coherent reasoning can still violate logical or evidential constraints, allowing…

Safety alignment can make frontier LMs overly conservative, degrading collaboration via hedging or false refusals. We present a lightweight toolkit with three parts: (1) Victor Calibration (VC), a multi-pass protocol that elicits a scalar…

Face verification systems have seen substantial advancements; however, they often lack transparency in their decision-making processes. In this paper, we introduce an innovative Vision-Language Model (VLM) for Face Verification, which not…

Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches,…

Theorem proving is fundamental to program verification, where the automated proof of Verification Conditions (VCs) remains a primary bottleneck. Real-world program verification frequently encounters hard VCs that existing Automated Theorem…

We present a transductive learning algorithm that takes as input training examples from a distribution $P$ and arbitrary (unlabeled) test examples, possibly chosen by an adversary. This is unlike prior work that assumes that test examples…

Large language models are trained to refuse harmful requests, but can they accurately predict when they will refuse before responding? We investigate this question through a systematic study where models first predict their refusal…

Decentralized inference provides a scalable and resilient paradigm for serving large language models (LLMs), enabling fragmented global resource utilization and reducing reliance on centralized providers. However, in a permissionless…

Vision-Language Models (VLMs) have demonstrated strong capabilities in aligning visual and textual modalities, enabling a wide range of applications in multimodal understanding and generation. While they excel in zero-shot and transfer…

Prediction, where observed data is used to quantify uncertainty about a future observation, is a fundamental problem in statistics. Prediction sets with coverage probability guarantees are a common solution, but these do not provide…

Many safety failures in machine learning arise when models are used to assign predictions to people (often in settings like lending, hiring, or content moderation) without accounting for how individuals can change their inputs. In this…

Sentence embedding is one of the most fundamental tasks in Natural Language Processing and plays an important role in various tasks. The recent breakthrough in sentence embedding is achieved by pre-trained language models (PLMs). Despite…