Related papers: SAGE Celer 2.6 Technical Card

We present Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning. Seed1.5-VL is composed with a 532M-parameter vision encoder and a Mixture-of-Experts (MoE) LLM of 20B…

Extending large language models (LLMs) to process longer inputs is crucial for a wide range of applications. However, the substantial computational cost of transformers and limited generalization of positional encoding restrict the size of…

We introduce SealQA, a new challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields conflicting, noisy, or unhelpful results. SealQA comes in three flavors: (1) Seal-0 (main) and…

While Vision-Language Models (VLMs) have shown promising progress in general multimodal tasks, they often struggle in industrial anomaly detection and reasoning, particularly in delivering interpretable explanations and generalizing to…

In this paper, we propose a novel encoder-decoder architecture, named SABER, to learn the 6D pose of the object in the embedding space by learning shape representation at a given pose. This model enables us to learn pose by performing shape…

Free-text promptable 3D medical image segmentation offers an intuitive and clinically flexible interaction paradigm. However, current methods are highly sensitive to linguistic variability: minor changes in phrasing can cause substantial…

Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep analysis and handling complex edge cases. While recent reasoning models demonstrate the…

We present TEGCER, an automated feedback tool for novice programmers. TEGCER uses supervised classification to match compilation errors in new code submissions with relevant pre-existing errors, submitted by other students before. The dense…

We present Semantic-Aware Guided Exploration, SAGE, a system for open-vocabulary exploration in unknown 3D indoor environments that preserves coverage-oriented behavior while allowing semantic cues to reprioritize frontier selection.…

While large language models (LLMs) have demonstrated remarkable performance on high-level semantic tasks, they often struggle with fine-grained, token-level understanding and structural reasoning--capabilities that are essential for…

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

The sixth-generation (6G) mobile network is envisioned to incorporate sensing and edge artificial intelligence (AI) as two key functions. Their natural convergence leads to the emergence of Integrated Sensing and Edge AI (ISEA), a novel…

Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging. Existing methods heavily…

Large Language Models (LLMs), such as OpenAI's o1-series have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism. However, recent studies reveal substantial…

This paper introduces NeCTAr (Near-Cache Transformer Accelerator), a 16nm heterogeneous multicore RISC-V SoC for sparse and dense machine learning kernels with both near-core and near-memory accelerators. A prototype chip runs at 400MHz at…

Unfair stereotypical biases (e.g., gender, racial, or religious biases) encoded in modern pretrained language models (PLMs) have negative ethical implications for widespread adoption of state-of-the-art language technology. To remedy for…

Large Language Models (LLMs) achieve strong performance on standard knowledge evaluation benchmarks, yet recent work shows that their knowledge capabilities remain brittle under question variants that test the same knowledge in different…

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

Training on verifiable symbolic data is a promising way to expand the reasoning frontier of language models beyond what standard pre-training corpora provide. Yet existing procedural generators often rely on fixed puzzles or templates and…

In this paper, we study the content-aware layout generation problem, which aims to automatically generate layouts that are harmonious with a given background image. Existing methods usually deal with this task with a single-step reasoning…