Abstract

This thesis develops and analyzes an adaptive framework for coordinated dual-arm manipulation that
integrates reinforcement learning with optimization-based variable impedance control. Building on the
DA-VIL approach, the work addresses the core challenge of dual-arm tasks: maintaining stable, precise
coordination under changing object properties and strongly coupled arm-object dynamics.
The proposed pipeline uses a learned policy (trained with PPO) to predict time-varying Cartesian
stiffness parameters, and an optimization (QP)-based controller that converts those impedance settings
into joint accelerations and torques while enforcing physical constraints (joint limits, velocity/torque
bounds, and end-effector geometry).
The thesis presents design choices for the policy and reward structure (including an EMA regularizer
for smooth stiffness trajectories), the QP formulation for simultaneous impedance and postural tasks,
and extensive MuJoCo evaluations on a diverse set of large objects with varying masses and geometries.
Quantitative results show consistent reductions in object trajectory-tracking error and improved robustness compared to baseline controllers (fixed impedance, optimization-only, and straightforward
RL+IC). Ablations highlight the importance of smooth stiffness predictions and the combined RL+QP
architecture. The thesis concludes with a discussion of limitations, potential extensions to assembly and
obstacle-aware planning, and plans for sim-to-real transfer and hardware validation.

Abstract

This study seeks to examine India's position within the global data economy, using three analytical
approaches. First, it assesses the extent to which dependency theory and world systems theory, originally
developed to analyse colonial and post-colonial economic relationships, may provide a useful lens for
understanding relationships between actors in the contemporary global digital economy, with data as a
central resource. Within this framework, it characterises the 'core', 'periphery', and 'semi-periphery' of
the data economy, and identifies attributes that would place India within the semi-periphery. This 'middle' position is examined further by exploring India's regulatory approach to cross-border data flows, as
reflected in its domestic legislation and international trade negotiations. The study characterises this as
a 'quasi-localisation' approach, placing onus on the Government of India to flexibly decide the kinds of
data, recipient countries, and transferring entities involved in permitted data transfers. Hence, in such
a context, it would be useful to analyse the government's priorities over time with respect to India's
domestic and international positions in the digital landscape. Thus, the study finally traces how the
Government of India's discourse around the digital economy has evolved over the period 2015 to 2025
within official government communications, and what this may indicate about the priorities and orientation of domestic digital policy.
The study finds that the global data economy appears to exhibit characteristics broadly consistent
with a core-semiperiphery-periphery framework, in which a small number of actors capture a disproportionate share of economic value from global data flows. Countries that exemplify the core are capable
of exerting a significant degree of structural control over other actors through technical, regulatory, and
policy standards, and are able to retain most of the value generated in the landscape. Countries positioned as semi-peripheral actors exhibit growing domestic technological capabilities and a degree of
strategic positioning in trade and regulatory negotiations, while remaining dependent on core actors for
key aspects of digital infrastructure. Some countries that may be analysed to be peripheral actors, are
dependent on core countries for fundamental infrastructure through various mechanisms. Through this
study, India is evaluated to occupy a place in the semi-periphery of the global data economy.
India's domestic data governance approach is characterised in this study as one of 'quasi-localisation',
which is consistent with its 'middle' semi-peripheral position globally. This characterisation was made
observing India's position as neither one of strict data localisation nor of complete support for the free
flow of data, but rather a strategically ambiguous intermediate stance that preserves substantial discre tionary power for the Government of India. This characterisation draws on an analysis of successive
versions of the Digital Personal Data Protection (DPDP) draft bills, the DPDP Act 2023, and the DPDP
Rules 2025, as well as India's strategic participation in international trade negotiations and agreements
with digital trade provisions.
The question of discretionary power to the Government of India lends itself to a consideration of
the evolving priorities of the government over time, for which this study undertakes a computational
text analysis of 8,532 Press Information Bureau press releases, selected from a total corpus of 1,33,902
collected over the period 2015 to 2025. The time period starts from the year of the launch of the Digital
India Mission, and concludes in the year of the release of the DPDP Rules, and hence provides a broad
overview of various developments in India's digital landscape. The analysis finds that certain subthemes
consistently dominated government communications throughout the period, namely those concerned
with national tech missions, while privacy and data flows related discourse has remained considerably
smaller in volume, albeit growing from 2022 onward. The largest volume of discourse happens at the
scale of the 'nation', with the 'local' and 'international' scales seeing a smaller amount of activity. A
small number of ministries, principally the Prime Minister's Office and the Ministry of Electronics and
Information Technology, dominate across subthemes and scale frames, however the presence of other
ministries points to a growing impact of the digital landscape on India's overall governance and its discourse.
Overall, the study locates India as a semi-peripheral actor in the global data economy, characterising its domestic data governance approach as a 'quasi-localisation' approach, and identifies themes of
growth and development as dominant within the domestic governance discourse

Abstract

The rapid adoption of large language models (LLMs) in applications such as recruitment, content
generation, and decision support has raised critical concerns regarding fairness and bias in automated
text generation. This thesis presents a comprehensive investigation into gender and occupational bias
in LLM-generated narratives, combining theoretical formulation, large-scale empirical analysis, and
multilingual evaluation across three complementary studies.
At the foundational level, this work formalizes bias in generative AI using a statistical framework,
defining bias as the deviation between generated outputs and an ideal, unbiased representation. Building
on this, a robust bias quantification pipeline is introduced, incorporating measures such as mean bias
(MB), mean absolute bias (MAB), sentiment analysis, and probabilistic distribution distances. Using
a large dataset of over 11,000 AI-generated job narratives, the study demonstrates that LLM outputs
exhibit measurable and consistent gender bias, particularly in the association of male entities with highintensity, high-stress, and challenging occupations.
Extending beyond single-model analysis, the thesis further explores bias across multiple LLMs,
including Gemini, Mistral, LLaMA, and OpenAI models, and introduces a structured evaluation framework based on narrative sentiment, syntactic agency, and a derived prestige score. The findings reveal
that gender bias persists across all models, though its magnitude and direction vary depending on model
architecture and prompt design. Notably, prompt framing is shown to significantly influence bias, with
negative or incompetence-related prompts consistently amplifying male representation.
A key contribution of this work is its multilingual analysis of bias in English and Telugu, addressing
a gap in existing research that predominantly focuses on high-resource languages. The results highlight
that while bias is present across both languages, its manifestation differs structurally: English narratives
show greater sentiment variability, whereas Telugu narratives exhibit higher agency representations.
These findings underscore the importance of linguistic context in shaping model behavior.
Overall, this thesis contributes a unified, scalable, and interpretable framework for analyzing bias
in generative AI systems. By integrating statistical rigor, large-scale datasets, cross-model comparison,
and multilingual evaluation, the work advances understanding of how bias emerges and propagates in
LLM-generated text and provides a foundation for developing more fair, transparent, and inclusive AI
systems.

Abstract

Robotic manipulation of large and complex objects requires not only the ability to generate feasible grasps, but also to ensure stability under multi-contact interactions, particularly in dual-arm
settings. While recent advances in data-driven grasp synthesis have shown promising results for
single-arm grasping, extending these methods to dual-arm scenarios introduces additional challenges such as coordinated contact placement, force balance, and collision avoidance. This thesis
addresses these challenges through a unified progression from generative modeling to analytical understanding, which are subsequently combined into an end-to-end framework for dual-arm grasp
generation.
We begin with Constrained GraspDiffusion Fields (CGDF), a diffusion-based generativemodelfor
6-DoF grasp synthesis on complex objects. CGDF introduces a part-guided diffusionmechanism that
enables sample-efficient generation of grasps constrained to specific regions of an object, allowing
dense and targeted grasp proposals even on large and geometrically intricate shapes. This provides
a strong foundation for generating diverse and region-aware grasp candidates.
Building on this, we recognize that dual-arm grasping requires a principled notion of stability beyond independent single-arm grasps. To address this, we developed DG16M, a large-scale dataset
and an analytical framework for evaluating dual-arm grasp stability using an optimization-based
force-closure formulation. By explicitly modeling contact forces, friction constraints, and external
disturbances, this work provides a physically grounded metric for assessing grasp quality and enables the learning of stability-aware models.
Finally, we integrate these two perspectives-- generativemodeling and analytical evaluation into
DAGDiff, an end-to-end diffusion-based framework for directly generating dual-arm grasp pairs.
Unlike prior approaches that rely on heuristic pairing or region selection, DAGDiff formulates grasp
generation in the joint SE(3)×SE(3)space and incorporates guidance from stability and collisionaware classifiers during the diffusion process. This allows the model to generate dual-arm grasps
that are not only diverse, but alsoforce-closure stable and collision-free directlyfrom raw input point
clouds.
Together, these contributions establish a principled pipeline for dual-arm grasp synthesis: from
region-aware generative modeling, to analytical stability evaluation, to fully integrated end-to-end
learning. This work advances the state of robotic manipulation by enabling reliable, generalizable,
and physically grounded dual-arm grasping on complex real-world objects.

Abstract

Solid organ transplantation remains the definitive therapeutic intervention for end-stage organ failure, yet long-term graft survival continues to be limited by allograft rejection, a complex immunemediated process traditionally studied on an organ-specific basis. This thesis presents a network-based
systems biology framework to identify a conserved, pan-organ molecular architecture of rejection. To
establish a unified framework beyond organ-specific studies, we performed a network-based systems
biology analysis of transcriptomic data from 672 liver, kidney, and heart transplant biopsies to identify a
conserved, pan-organ molecular framework of rejection. By constructing and comparing organ-specific
gene co-expression networks, we identified a consensus, six-module immune cascade that captures the
hierarchical nature of the alloimmune response. In addition, we also uncovered a highly conserved
24-gene cell cycle signature consistently upregulated in rejecting allografts, implicating cellular proliferation as a core feature of rejection pathology. From this framework, we derived a 172-gene immune
signature and applied machine learning models to assess its predictive performance, achieving accuracy comparable to established benchmarks. We further refined this to a minimal, high-performance
20-gene immune signature (AUC > 0.96). Both the immune and cell cycle signatures demonstrated robust, pan-organ utility when independently validated in a lung transplant cohort (n=243). Collectively,
these findings define a pan-organ molecular framework for rejection and highlight cell cycle dysregulation as a conserved hallmark, offering a foundation for standardized, cross-organ diagnostic platforms
to improve allograft surveillance and patient outcomes. Shifting from the post-transplant graft to the
pre-transplant systemic immune state, peripheral blood mononuclear cell profiling of kidney transplant
recipients revealed a baseline immunometabolic state defined by selective cytotoxic immune depletion and dysregulation of eicosanoid and fatty acid metabolism, consolidated into a predictive 15-gene
PBMC biomarker panel (AUC = 0.836). Collectively, these findings establish that the immunological
fate of a transplanted organ is shaped not only by post-transplant alloimmune programs but also by a
metabolic and immune landscape already present in the recipient before surgery

Abstract

Stroke often results in motor speech disorders such as dysarthria, leading to reduced speech intelligibility and impaired communication. Accurate assessment of speech intelligibility and identification of
underlying articulatory deficits are essential for effective rehabilitation. However, existing approaches
largely rely on subjective evaluation or global scoring, offering limited support for targeted therapy
planning, particularly in under-resourced languages such as Telugu.
This work presents an objective and interpretable framework for assessing speech intelligibility and
articulatory impairments in Telugu-speaking post-stroke individuals. A phonemically structured speech
corpus was developed, comprising recordings from 13 stroke participants along with perceptual intelligibility ratings obtained from human evaluators. In addition, speech data from 25 age-matched healthy
participants were collected as part of a pilot study to establish a reference dataset. Word-level intelligibility was estimated using Dynamic Time Warping (DTW) applied to embeddings derived from the
Wav2Vec2-Large-XLSR-53-Telugu model, and validated against listener judgments.
To enable detailed analysis beyond global scoring, a minimal pairs based articulatory mapping framework was proposed. By analyzing phonological contrasts such as place of articulation and voicing, the
framework identifies consistent phoneme-level errors and maps them to probable articulatory subsystems. This approach provides a meaningful link between acoustic speech deviations and underlying
physiological mechanisms.
In addition, a combined analysis of word-level and passage-level speech was performed to capture
both articulatory precision and performance in conversational speech. The results highlight the heterogeneous nature of post-stroke speech impairment, with deficits often localized to specific phoneme
groups or arising from coordination challenges in continuous speech. The findings also emphasize the
importance of considering dialectal variation in speech assessment.
Beyond overall intelligibility assessment, the proposed framework enables phoneme-level analysis
of speech errors. By identifying consistently misarticulated phonemes and mapping them to underlying
articulatory subsystems, it provides interpretable insights that can support targeted therapy planning. In
summary, proposed approach employs phonemic-level assessment to identify speech impairments and
provides articulator specific insights, enabling therapists to design targeted interventions using phoneticlevel measures. This approach contributes toward the development of data driven and personalized
rehabilitation strategies for dysarthric speech in Telugu.

Abstract

Large Language Models (LLMs) exhibit strong performance on reasoning and semantic understanding tasks in high-resource languages such as English. However, their effectiveness in low-resource and
morphologically rich languages remains less well understood. This thesis examines the limitations of
multilingual language models in such settings through a combined study of evaluation benchmarks,
empirical analysis, and cross-lingual modeling behavior, with a primary focus on Telugu.
The thesis brings together three complementary lines of work. First, it introduces TeluguEval, a
human-curated, multi-domain benchmark designed to evaluate reasoning across mathematical, commonsense, scientific, legal, and ethical tasks in Telugu. Second, it presents a systematic evaluation
of large multilingual and region-specific models across English, Telugu script, and Romanized Telugu
inputs, highlighting consistent performance degradation in low-resource settings. Third, it analyzes classification and translation-based scenarios to examine how multilingual modeling choices and translation
quality influence downstream semantic understanding.
Across these settings, the results reveal recurring challenges, including sensitivity to script variation,
inefficiencies arising from tokenization, biases in answer selection, unintended code-switching, and
reduced reliability on multi-step reasoning tasks. The findings indicate that strong English performance
or high-quality translation does not necessarily translate to robust reasoning or semantic competence in
low-resource languages. Overall, this thesis underscores the importance of targeted evaluation resources
and careful empirical analysis for understanding and improving multilingual language models beyond
high-resource languages.

Abstract

People and large language models both respond to social relationships, but they do so in different
ways. Studies of social distance in economic games show mixed results: some find that people treat
close others more generously, while others find no effect. This thesis argues that this inconsistency
reflects a structural principle: social ties influence behavior only when the task requires reasoning about
a specific person, and not when shared norms already guide decisions. This account is tested in humans
and in large language models.
Study 1 examined naturally occurring dyads with no tie, weak tie, or strong tie. Participants played
three economic games: Dictator, Ultimatum, and Centipede. At each decision, participants also reported their beliefs about their co-player. Tie strength did not change offers or beliefs in the Dictator or
Ultimatum games, both of which involve strong fairness expectations that apply regardless of the relationship between players. In the Centipede Game, strong-tie pairs cooperated 1.47 rounds longer than
no-tie pairs and expected co-players to stop 1.14 rounds later. Both effects remained significant after
multiple-comparison correction. Beliefs predicted behavior across all groups, and strong ties predicted
longer cooperation even after controlling for observer expectations.
Study 2 tested two large language models, Mistral 7B Instruct and Llama 3 8B Instruct, on the same
three games. Prompts varied the tie label, behavioral history, and history type in a full factorial design
across thousands of trials. The selective pattern found in humans was not observed in the models. Tie
effects were present across all three games for both models, with no concentration in the task where
predicting a specific partner is most important. Notably, the social tie effect in the Dictator Game
(η
2
p = .137 for LLaMA Action) was larger than in the Centipede Game (η
2
p = .030). This indicates
a failure of selectivity rather than a lack of sensitivity to social cues. Relational language appears to
function as a general cooperative bias rather than information used only when it is strategically relevant.
Llama 3 8B showed larger and more consistent tie effects than Mistral 7B, likely reflecting alignment
training rather than stronger relational reasoning.
Humans and current language models therefore differ not in whether they respond to social ties, but
in how they use them. Humans apply relational knowledge selectively, using it where shared norms
do not provide a clear script and partner-specific reasoning is needed. The models apply relational
cues more broadly, regardless of whether the task makes them useful. These findings show that social
reasoning in humans is sensitive to task structure, while in current models it operates as a more general
bias, highlighting a key difference that warrants further investigation.

Abstract

This thesis examines polycrisis as a condition of interdependent and mutually reinforcing crises, focusing on the Western Himalayan region encompassing Himachal Pradesh and Uttarakhand. In recent
years, the term polycrisis has gained prominence to describe situations in which environmental, economic, political, and social stresses overlap in ways that blur causal boundaries and complicate policy
responses. While existing studies have extensively analysed individual crises in the Western Himalayas
such as climate change impacts, agricultural stress, migration, and disaster risk, these processes are often
examined in isolation. This thesis argues that such siloed approaches are insufficient for understanding
the region's systemic vulnerability.
The central contribution of this work is the development of a structured modeling framework that
represents polycrisis as an interconnected system rather than a collection of parallel challenges. Our
approach begins by identifying four main domains of environmental, economic, political and social
aspects of polycrisis. Within these, we select key variables (nodes) such as climate change, migration,
agricultural productivity, and disaster preparedness and governance; each broken down into concomitant
sub-factors (subnodes). Using an extensive review of peer-reviewed literature, government reports, and
region-specific case studies, the thesis systematically maps both first-order relationships between nodes
and the subnodes and second-order relationships between subnodes themselves. This two-level mapping
reveals feedback loops and cascading pathways that are often obscured in domain-specific analyses.
Across both mapping iterations, that is first-order relationships (node ↔ subnode) being the first iteration and second-order relationships (subnode ↔ subnode) being the second iteration, the thesis identifies and documents approximately 120 relationships, which are categorised using a five-point ordinal
scale ranging from Very Strong to Negligible. This categorisation is grounded in empirical evidence
and conceptual studies centered around Western Himalayas or comparable mountain ranges. The resulting network highlights the centrality of climatic variables, the mediating role of governance, and the
reinforcing interactions between agricultural stress and migration.
The framework serves as a proof of concept for simulating cascading effects across socio-ecological
systems and informing anticipatory policy responses in mountainous regions under stress by addressing
how multiple, co-occurring crises interact across environmental, economic, political, and social systems
to constitute a regional polycrisis, and proposes a systematic model to represent and quantify these
linkages.

Abstract

Music has historically functioned as a primary vehicle for political expression and transforming personal struggles into collective narratives of resistance. While the cultural and historical significance of
protest music is well documented, its specific linguistic and acoustic signatures, the quantifiable features that differentiate it from general music remain largely underexplored. This thesis presents Voices
of Dissent, a comprehensive multimodal computational framework designed to analyze and characterize protest music through the dual lenses of natural language processing and audio analysis. To address
the scarcity of specialized resources, we first curate a novel, balanced multimodal dataset comprising
458 protest songs (sourced via Wikidata) and 370 non protest songs (matched by time period and genre
diversity using GPT-4 inference). Our methodology follows a multi step approach: first, we extract
linguistic and audio features including lexical diversity, rhyme density, sentiment polarity, spectral flux
etc. to isolate the stylistic dimensions of dissent in lyrics and audio. Second, we evaluate a suite of transformer based models, to assess the performance of deep embeddings in capturing protest intent across
text and audio modalities. A key technical contribution of this work is the application of source separation to decompose audio tracks into vocal and accompaniment stems. By conducting controlled mixing
experiments, we quantify the relative influence of the "message" (vocal delivery) versus the "medium"
(instrumental arrangement) in the perception of protest. Our results indicate that protest lyrics exhibit
significantly higher repetition and more negative valence compared to non protest counterparts. Furthermore, text based models (91.10% F1-score) slightly outperform audio-based models (90.62% F1-score),
though the high performance of both suggests that protest signals are deeply embedded in both modalities. To validate these computational findings on the audio side, we conduct a human annotation study
involving 50 participants, revealing a strong correlation between automated feature extraction and human perception of musical energy, vocal roughness, and melodic disjunctness. This research provides
empirical grounding for the study of protest music, offering a scalable framework for researchers in
musicology, sociolinguistics, and digital activism to analyze the evolving language of resistance in the
digital age.